mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-07-31 12:30:30 +08:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
21020fb334 | ||
|
|
a243d78d32 | ||
|
|
66512fa808 | ||
|
|
7efd03fb3b | ||
|
|
e1b89f5aaf | ||
|
|
32dd522d5a | ||
|
|
eeb0373033 | ||
|
|
facade7d00 | ||
|
|
08e796401a | ||
|
|
f8e8ab669d | ||
|
|
5e0b1a2b69 | ||
|
|
667941aaa8 | ||
|
|
011fb81cc3 | ||
|
|
5c06b57cea | ||
|
|
0680f01bf7 | ||
|
|
186c1075ce | ||
|
|
b161a5c288 | ||
|
|
4f018c91d7 | ||
|
|
63949d45e2 | ||
|
|
399c1d0e02 | ||
|
|
89717dca56 | ||
|
|
c8bf74a516 | ||
|
|
4e551e432f | ||
|
|
60add6da49 | ||
|
|
ddcadce542 | ||
|
|
5cefd3a108 | ||
|
|
713dd5c71a | ||
|
|
678d5aacc5 | ||
|
|
b3f4ab7452 | ||
|
|
7b4b9feaa5 | ||
|
|
add423f762 | ||
|
|
c34ce15fa2 | ||
|
|
8e637041c4 | ||
|
|
146cec3c08 | ||
|
|
14a62e3451 | ||
|
|
7e29e408af | ||
|
|
30bc131b97 | ||
|
|
1b0118c365 | ||
|
|
cda73e5ebf | ||
|
|
b0eda78d3f | ||
|
|
bf682bdb62 | ||
|
|
b322622117 | ||
|
|
415450e785 | ||
|
|
1d488f0117 | ||
|
|
4e789208b4 | ||
|
|
cdd4dc7302 | ||
|
|
60708e1e8b | ||
|
|
5a324f99ae | ||
|
|
d5778dfafb | ||
|
|
68c251830c | ||
|
|
2aa2d73d2d | ||
|
|
58bd390fbd | ||
|
|
2707901239 | ||
|
|
a5ed2de8a8 | ||
|
|
21893dda58 | ||
|
|
758a2f3d49 | ||
|
|
0331f14f19 | ||
|
|
138b131a35 | ||
|
|
55c0d5c7fd | ||
|
|
e98a7a8260 | ||
|
|
7e7787cb23 | ||
|
|
c4b508f045 | ||
|
|
52e7853d21 | ||
|
|
d43061f722 | ||
|
|
7b10fd47d8 | ||
|
|
95f2c87bfa | ||
|
|
c756fc51e0 | ||
|
|
386db75669 | ||
|
|
e3dc2e6f4c | ||
|
|
70c8757fc0 | ||
|
|
b794150ed9 |
@@ -0,0 +1,225 @@
|
||||
name: Auto-merge Speakeasy PR
|
||||
|
||||
# Called as a follow-up job after Speakeasy Generate (mode: pr). Merges the
|
||||
# regen PR opened/updated in the same workflow run so sdk_publish.yaml can run.
|
||||
# Prefer branch_name from Generate logs; fall back to run_started_at heuristics.
|
||||
# Uses GH_DOCS_SYNC GitHub App token (not a PAT) so merges trigger downstream push.
|
||||
|
||||
on:
|
||||
workflow_call:
|
||||
inputs:
|
||||
run_started_at:
|
||||
description: ISO timestamp when the parent Generate workflow run started
|
||||
required: true
|
||||
type: string
|
||||
branch_name:
|
||||
description: Speakeasy regen branch from the parent Generate run (optional)
|
||||
required: false
|
||||
type: string
|
||||
default: ""
|
||||
secrets:
|
||||
GH_DOCS_SYNC_APP_ID:
|
||||
required: true
|
||||
GH_DOCS_SYNC_APP_PRIVATE_KEY:
|
||||
required: true
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: write
|
||||
|
||||
concurrency:
|
||||
group: auto-merge-speakeasy
|
||||
cancel-in-progress: false
|
||||
|
||||
jobs:
|
||||
auto-merge:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Generate GitHub App token
|
||||
id: app-token
|
||||
# actions/create-github-app-token@v3.2.0 (immutable SHA)
|
||||
uses: actions/create-github-app-token@bcd2ba49218906704ab6c1aa796996da409d3eb1
|
||||
with:
|
||||
app-id: ${{ secrets.GH_DOCS_SYNC_APP_ID }}
|
||||
private-key: ${{ secrets.GH_DOCS_SYNC_APP_PRIVATE_KEY }}
|
||||
|
||||
- name: Resolve Speakeasy regen PR
|
||||
id: pr
|
||||
env:
|
||||
GH_TOKEN: ${{ steps.app-token.outputs.token }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
REPO="${{ github.repository }}"
|
||||
RUN_STARTED="${{ inputs.run_started_at }}"
|
||||
BRANCH="${{ inputs.branch_name }}"
|
||||
|
||||
PR_JSON=$(gh pr list \
|
||||
--repo "$REPO" \
|
||||
--state open \
|
||||
--search "head:speakeasy-sdk-regen-" \
|
||||
--limit 500 \
|
||||
--json number,updatedAt,title,labels,author,headRefName)
|
||||
|
||||
PR_NUM=""
|
||||
if [ -n "$BRANCH" ]; then
|
||||
CANDIDATE=$(echo "$PR_JSON" | jq -r --arg branch "$BRANCH" \
|
||||
'[.[] | select(.headRefName == $branch)] | .[0] // empty')
|
||||
if [ -n "$CANDIDATE" ] && echo "$CANDIDATE" | jq -e '
|
||||
(.headRefName | startswith("speakeasy-sdk-regen-"))
|
||||
and (.title | contains("🐝 Update SDK"))
|
||||
and ([.labels[].name] | any(. == "patch" or . == "minor" or . == "major"))
|
||||
and (.author.is_bot == true)
|
||||
' > /dev/null; then
|
||||
PR_NUM=$(echo "$CANDIDATE" | jq -r '.number')
|
||||
echo "Resolved Speakeasy regen PR #$PR_NUM from branch $BRANCH"
|
||||
else
|
||||
echo "::warning::branch_name=$BRANCH did not match a valid open regen PR — falling back to run_started_at"
|
||||
fi
|
||||
fi
|
||||
|
||||
if [ -z "$PR_NUM" ]; then
|
||||
PR_NUM=$(echo "$PR_JSON" | jq -r --arg started "$RUN_STARTED" '
|
||||
[.[]
|
||||
| select(.headRefName | startswith("speakeasy-sdk-regen-"))
|
||||
| select(.title | contains("🐝 Update SDK"))
|
||||
| select([.labels[].name] | any(. == "patch" or . == "minor" or . == "major"))
|
||||
| select(.author.is_bot == true)
|
||||
| select(.updatedAt >= $started)
|
||||
] | sort_by(.updatedAt) | last | .number // empty')
|
||||
fi
|
||||
|
||||
if [ -z "$PR_NUM" ]; then
|
||||
echo "No Speakeasy regen PR for this Generate run — skipping auto-merge"
|
||||
echo "::notice title=auto-merge-skipped::No qualifying Speakeasy regen PR to merge"
|
||||
{
|
||||
echo "## Auto-merge skipped"
|
||||
echo "No qualifying \`speakeasy-sdk-regen-*\` PR was found."
|
||||
echo "- branch_name input: \`${BRANCH:-<empty>}\`"
|
||||
echo "- run_started_at: \`$RUN_STARTED\`"
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
echo "pr_num=" >> "$GITHUB_OUTPUT"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
echo "pr_num=$PR_NUM" >> "$GITHUB_OUTPUT"
|
||||
echo "$PR_JSON" > /tmp/speakeasy_pr_json.json
|
||||
|
||||
- name: Close superseded Speakeasy PRs
|
||||
if: steps.pr.outputs.pr_num != ''
|
||||
env:
|
||||
GH_TOKEN: ${{ steps.app-token.outputs.token }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
CURRENT_PR="${{ steps.pr.outputs.pr_num }}"
|
||||
PR_JSON=$(cat /tmp/speakeasy_pr_json.json)
|
||||
|
||||
PRIOR_JSON=$(echo "$PR_JSON" | jq -r --arg current_pr "$CURRENT_PR" \
|
||||
'[.[].number | select(tostring != $current_pr)] | .[]')
|
||||
|
||||
if [ -z "$PRIOR_JSON" ]; then
|
||||
echo "No superseded Speakeasy PRs to close"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
mapfile -t PRIOR <<< "$PRIOR_JSON"
|
||||
|
||||
echo "Closing ${#PRIOR[@]} superseded Speakeasy PR(s)"
|
||||
for N in "${PRIOR[@]}"; do
|
||||
gh pr close "$N" --repo "${{ github.repository }}" --delete-branch \
|
||||
--comment "Superseded by newer Speakeasy SDK generation PR #${CURRENT_PR}" \
|
||||
|| echo "::warning::Failed to close PR #$N (continuing)"
|
||||
sleep 1
|
||||
done
|
||||
|
||||
- name: Auto-merge Speakeasy PR
|
||||
if: steps.pr.outputs.pr_num != ''
|
||||
env:
|
||||
GH_TOKEN: ${{ steps.app-token.outputs.token }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
PR_NUM="${{ steps.pr.outputs.pr_num }}"
|
||||
REPO="${{ github.repository }}"
|
||||
|
||||
wait_for_checks() {
|
||||
local pr=$1
|
||||
local timeout=600
|
||||
local interval=15
|
||||
local elapsed=0
|
||||
|
||||
echo "Waiting for PR #$pr checks (timeout ${timeout}s)..."
|
||||
while [ "$elapsed" -lt "$timeout" ]; do
|
||||
TOTAL=$(gh pr view "$pr" --repo "$REPO" --json statusCheckRollup --jq \
|
||||
'.statusCheckRollup | length')
|
||||
PENDING=$(gh pr view "$pr" --repo "$REPO" --json statusCheckRollup --jq \
|
||||
'[.statusCheckRollup[]? | select(.status != "COMPLETED")] | length')
|
||||
FAILED=$(gh pr view "$pr" --repo "$REPO" --json statusCheckRollup --jq \
|
||||
'[.statusCheckRollup[]? | select(.status == "COMPLETED") | select(.conclusion != "SUCCESS" and .conclusion != "SKIPPED" and .conclusion != "NEUTRAL")] | length')
|
||||
|
||||
if [ "$TOTAL" -eq 0 ]; then
|
||||
# GITHUB_TOKEN-authored regen PRs get no pull_request checks at all,
|
||||
# so TOTAL stays 0 forever. Wait a short grace window in case checks
|
||||
# are merely slow to register, then proceed rather than time out.
|
||||
if [ "$elapsed" -ge 60 ]; then
|
||||
echo "No checks registered after ${elapsed}s — proceeding (checkless PR)"
|
||||
return 0
|
||||
fi
|
||||
echo "Checks not yet registered — waiting ${interval}s..."
|
||||
sleep "$interval"
|
||||
elapsed=$((elapsed + interval))
|
||||
continue
|
||||
fi
|
||||
|
||||
if [ "$PENDING" -eq 0 ]; then
|
||||
if [ "$FAILED" -gt 0 ]; then
|
||||
echo "::error::PR #$pr has failing checks — refusing direct merge"
|
||||
gh pr checks "$pr" --repo "$REPO" || true
|
||||
exit 1
|
||||
fi
|
||||
echo "All checks completed"
|
||||
return 0
|
||||
fi
|
||||
|
||||
echo "Checks pending ($PENDING) — waiting ${interval}s..."
|
||||
sleep "$interval"
|
||||
elapsed=$((elapsed + interval))
|
||||
done
|
||||
|
||||
echo "::error::Timed out waiting for PR #$pr checks"
|
||||
exit 1
|
||||
}
|
||||
|
||||
STATE=$(gh pr view "$PR_NUM" --repo "$REPO" --json state --jq .state)
|
||||
if [ "$STATE" != "OPEN" ]; then
|
||||
echo "PR #$PR_NUM is $STATE — skipping merge"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
MERGE_METHOD=""
|
||||
# Prefer GitHub auto-merge when required checks exist; otherwise
|
||||
# squash-merge directly after checks pass (sdk-release-prs.yaml pattern).
|
||||
AUTO_MERGE_NOOP_PATTERN='is in clean status|protected branch rules|Branch does not have required protected branch rules'
|
||||
if gh pr merge "$PR_NUM" --repo "$REPO" --squash --auto --delete-branch 2> /tmp/gh-merge.err; then
|
||||
MERGE_METHOD="auto-merge queued"
|
||||
echo "Auto-merge enabled for Speakeasy PR #$PR_NUM"
|
||||
elif grep -qiE "$AUTO_MERGE_NOOP_PATTERN" /tmp/gh-merge.err; then
|
||||
echo "Auto-merge not applicable — waiting for checks, then merging PR #$PR_NUM directly"
|
||||
cat /tmp/gh-merge.err >&2
|
||||
wait_for_checks "$PR_NUM"
|
||||
gh pr merge "$PR_NUM" --repo "$REPO" --squash --delete-branch
|
||||
MERGE_METHOD="direct squash (checks passed)"
|
||||
else
|
||||
echo "::error::Failed to enable auto-merge on Speakeasy PR #$PR_NUM"
|
||||
cat /tmp/gh-merge.err >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "::notice title=auto-merge-pr::Merged Speakeasy PR #$PR_NUM ($MERGE_METHOD)"
|
||||
{
|
||||
echo "## Auto-merge complete"
|
||||
echo "- PR: #$PR_NUM"
|
||||
echo "- Method: $MERGE_METHOD"
|
||||
echo "- Token: GH_DOCS_SYNC GitHub App"
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
@@ -0,0 +1,37 @@
|
||||
name: PR Validation
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
paths-ignore:
|
||||
- .speakeasy/in.openapi.yaml
|
||||
|
||||
concurrency:
|
||||
group: pr-validation-${{ github.event.pull_request.number }}
|
||||
cancel-in-progress: true
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
validate:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v5
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v5
|
||||
with:
|
||||
enable-cache: true
|
||||
|
||||
- name: Build SDK
|
||||
run: uv build
|
||||
|
||||
- name: Type check (mypy)
|
||||
run: uv run --group dev mypy src
|
||||
|
||||
- name: Type check (pyright)
|
||||
run: uv run --group dev pyright src
|
||||
|
||||
- name: Lint (pylint)
|
||||
run: uv run --group dev pylint src --rcfile pylintrc
|
||||
@@ -21,6 +21,11 @@ permissions:
|
||||
types:
|
||||
- labeled
|
||||
- unlabeled
|
||||
|
||||
concurrency:
|
||||
group: speakeasy-generate
|
||||
cancel-in-progress: false
|
||||
|
||||
jobs:
|
||||
generate:
|
||||
uses: speakeasy-api/sdk-generation-action/.github/workflows/workflow-executor.yaml@v15
|
||||
@@ -32,3 +37,67 @@ jobs:
|
||||
github_access_token: ${{ secrets.GITHUB_TOKEN }}
|
||||
pypi_token: ${{ secrets.PYPI_TOKEN }}
|
||||
speakeasy_api_key: ${{ secrets.SPEAKEASY_API_KEY }}
|
||||
|
||||
resolve-branch:
|
||||
needs: generate
|
||||
if: ${{ !cancelled() && needs.generate.result == 'success' }}
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
branch_name: ${{ steps.branch.outputs.branch_name }}
|
||||
run_started_at: ${{ steps.branch.outputs.run_started_at }}
|
||||
steps:
|
||||
- name: Extract branch from Generate logs
|
||||
id: branch
|
||||
env:
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
REPO="${{ github.repository }}"
|
||||
RUN_ID="${{ github.run_id }}"
|
||||
|
||||
RUN_STARTED="${{ github.run_started_at }}"
|
||||
if [ -z "$RUN_STARTED" ]; then
|
||||
RUN_STARTED=$(gh run view "$RUN_ID" --repo "$REPO" --json startedAt --jq '.startedAt')
|
||||
echo "Resolved run_started_at from API: $RUN_STARTED"
|
||||
fi
|
||||
echo "run_started_at=$RUN_STARTED" >> "$GITHUB_OUTPUT"
|
||||
|
||||
# Full-run logs are unavailable while the workflow is in progress;
|
||||
# fetch logs from the completed generate job instead.
|
||||
JOB_ID=$(gh run view "$RUN_ID" --repo "$REPO" --json jobs --jq \
|
||||
'[.jobs[] | select(.name == "generate / Generate Target")] | .[0].databaseId // empty')
|
||||
|
||||
BRANCH=""
|
||||
if [ -z "$JOB_ID" ]; then
|
||||
echo "::warning::Could not find generate job id — auto-merge will use run_started_at fallback"
|
||||
else
|
||||
MAX_ATTEMPTS=12
|
||||
INTERVAL=10
|
||||
for attempt in $(seq 1 "$MAX_ATTEMPTS"); do
|
||||
BRANCH=$(gh run view "$RUN_ID" --repo "$REPO" --job "$JOB_ID" --log 2>/dev/null \
|
||||
| grep -oE 'branch_name=speakeasy-sdk-regen-[0-9]+' | tail -1 | cut -d= -f2 || true)
|
||||
if [ -n "$BRANCH" ]; then
|
||||
echo "Extracted branch_name=$BRANCH (attempt $attempt)"
|
||||
break
|
||||
fi
|
||||
if [ "$attempt" -lt "$MAX_ATTEMPTS" ]; then
|
||||
echo "Job logs not ready — waiting ${INTERVAL}s (attempt $attempt/$MAX_ATTEMPTS)..."
|
||||
sleep "$INTERVAL"
|
||||
fi
|
||||
done
|
||||
if [ -z "$BRANCH" ]; then
|
||||
echo "::warning::Could not extract branch_name from Generate logs after ${MAX_ATTEMPTS} attempts — auto-merge will use run_started_at fallback"
|
||||
fi
|
||||
fi
|
||||
echo "branch_name=$BRANCH" >> "$GITHUB_OUTPUT"
|
||||
|
||||
auto-merge:
|
||||
needs: [generate, resolve-branch]
|
||||
if: ${{ !cancelled() && needs.generate.result == 'success' }}
|
||||
uses: ./.github/workflows/auto-merge-speakeasy-pr.yaml
|
||||
with:
|
||||
run_started_at: ${{ needs.resolve-branch.outputs.run_started_at }}
|
||||
branch_name: ${{ needs.resolve-branch.outputs.branch_name }}
|
||||
secrets:
|
||||
GH_DOCS_SYNC_APP_ID: ${{ secrets.GH_DOCS_SYNC_APP_ID }}
|
||||
GH_DOCS_SYNC_APP_PRIVATE_KEY: ${{ secrets.GH_DOCS_SYNC_APP_PRIVATE_KEY }}
|
||||
|
||||
@@ -0,0 +1,104 @@
|
||||
name: Generate (spec change merged)
|
||||
permissions:
|
||||
checks: write
|
||||
contents: write
|
||||
pull-requests: write
|
||||
statuses: write
|
||||
id-token: write
|
||||
"on":
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
force:
|
||||
description: Force generation of SDKs
|
||||
type: boolean
|
||||
default: false
|
||||
set_version:
|
||||
description: optionally set a specific SDK version
|
||||
type: string
|
||||
pull_request:
|
||||
types: [closed]
|
||||
branches:
|
||||
- main
|
||||
paths:
|
||||
- .speakeasy/in.openapi.yaml
|
||||
|
||||
concurrency:
|
||||
group: speakeasy-generate-spec-change
|
||||
cancel-in-progress: false
|
||||
|
||||
jobs:
|
||||
generate:
|
||||
if: github.event.pull_request.merged == true || github.event_name == 'workflow_dispatch'
|
||||
uses: speakeasy-api/sdk-generation-action/.github/workflows/workflow-executor.yaml@v15
|
||||
with:
|
||||
force: ${{ github.event.inputs.force }}
|
||||
mode: pr
|
||||
set_version: ${{ github.event.inputs.set_version }}
|
||||
secrets:
|
||||
github_access_token: ${{ secrets.GITHUB_TOKEN }}
|
||||
pypi_token: ${{ secrets.PYPI_TOKEN }}
|
||||
speakeasy_api_key: ${{ secrets.SPEAKEASY_API_KEY }}
|
||||
|
||||
resolve-branch:
|
||||
needs: generate
|
||||
if: ${{ !cancelled() && needs.generate.result == 'success' }}
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
branch_name: ${{ steps.branch.outputs.branch_name }}
|
||||
run_started_at: ${{ steps.branch.outputs.run_started_at }}
|
||||
steps:
|
||||
- name: Extract branch from Generate logs
|
||||
id: branch
|
||||
env:
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
REPO="${{ github.repository }}"
|
||||
RUN_ID="${{ github.run_id }}"
|
||||
|
||||
RUN_STARTED="${{ github.run_started_at }}"
|
||||
if [ -z "$RUN_STARTED" ]; then
|
||||
RUN_STARTED=$(gh run view "$RUN_ID" --repo "$REPO" --json startedAt --jq '.startedAt')
|
||||
echo "Resolved run_started_at from API: $RUN_STARTED"
|
||||
fi
|
||||
echo "run_started_at=$RUN_STARTED" >> "$GITHUB_OUTPUT"
|
||||
|
||||
# Full-run logs are unavailable while the workflow is in progress;
|
||||
# fetch logs from the completed generate job instead.
|
||||
JOB_ID=$(gh run view "$RUN_ID" --repo "$REPO" --json jobs --jq \
|
||||
'[.jobs[] | select(.name == "generate / Generate Target")] | .[0].databaseId // empty')
|
||||
|
||||
BRANCH=""
|
||||
if [ -z "$JOB_ID" ]; then
|
||||
echo "::warning::Could not find generate job id — auto-merge will use run_started_at fallback"
|
||||
else
|
||||
MAX_ATTEMPTS=12
|
||||
INTERVAL=10
|
||||
for attempt in $(seq 1 "$MAX_ATTEMPTS"); do
|
||||
BRANCH=$(gh run view "$RUN_ID" --repo "$REPO" --job "$JOB_ID" --log 2>/dev/null \
|
||||
| grep -oE 'branch_name=speakeasy-sdk-regen-[0-9]+' | tail -1 | cut -d= -f2 || true)
|
||||
if [ -n "$BRANCH" ]; then
|
||||
echo "Extracted branch_name=$BRANCH (attempt $attempt)"
|
||||
break
|
||||
fi
|
||||
if [ "$attempt" -lt "$MAX_ATTEMPTS" ]; then
|
||||
echo "Job logs not ready — waiting ${INTERVAL}s (attempt $attempt/$MAX_ATTEMPTS)..."
|
||||
sleep "$INTERVAL"
|
||||
fi
|
||||
done
|
||||
if [ -z "$BRANCH" ]; then
|
||||
echo "::warning::Could not extract branch_name from Generate logs after ${MAX_ATTEMPTS} attempts — auto-merge will use run_started_at fallback"
|
||||
fi
|
||||
fi
|
||||
echo "branch_name=$BRANCH" >> "$GITHUB_OUTPUT"
|
||||
|
||||
auto-merge:
|
||||
needs: [generate, resolve-branch]
|
||||
if: ${{ !cancelled() && needs.generate.result == 'success' }}
|
||||
uses: ./.github/workflows/auto-merge-speakeasy-pr.yaml
|
||||
with:
|
||||
run_started_at: ${{ needs.resolve-branch.outputs.run_started_at }}
|
||||
branch_name: ${{ needs.resolve-branch.outputs.branch_name }}
|
||||
secrets:
|
||||
GH_DOCS_SYNC_APP_ID: ${{ secrets.GH_DOCS_SYNC_APP_ID }}
|
||||
GH_DOCS_SYNC_APP_PRIVATE_KEY: ${{ secrets.GH_DOCS_SYNC_APP_PRIVATE_KEY }}
|
||||
+1460
-311
File diff suppressed because one or more lines are too long
+1
-1
@@ -32,7 +32,7 @@ generation:
|
||||
skipResponseBodyAssertions: false
|
||||
preApplyUnionDiscriminators: true
|
||||
python:
|
||||
version: 0.9.2
|
||||
version: 0.10.6
|
||||
additionalDependencies:
|
||||
dev: {}
|
||||
main: {}
|
||||
|
||||
+3638
-177
File diff suppressed because it is too large
Load Diff
+3557
-140
File diff suppressed because it is too large
Load Diff
@@ -2,20 +2,20 @@ speakeasyVersion: 1.680.0
|
||||
sources:
|
||||
OpenRouter API:
|
||||
sourceNamespace: open-router-chat-completions-api
|
||||
sourceRevisionDigest: sha256:08108f43d4fba1406b4c8f624792054965c95a14819f442262663cb25ce6cc25
|
||||
sourceBlobDigest: sha256:47fc5915e6a9ff29fca019515d6491adce926407ebb47cee480feb77cfb68f03
|
||||
sourceRevisionDigest: sha256:c71a8e6b169e2ba8a81840f6ebeeb268ee09a440fb16b891f74fe2a9b065b989
|
||||
sourceBlobDigest: sha256:9d925b089f27563fa71967c94b8307007161626a685b84f4c4ab046b78b33f01
|
||||
tags:
|
||||
- latest
|
||||
- speakeasy-sdk-regen-1776991284
|
||||
- speakeasy-sdk-regen-1782497972
|
||||
- 1.0.0
|
||||
targets:
|
||||
open-router:
|
||||
source: OpenRouter API
|
||||
sourceNamespace: open-router-chat-completions-api
|
||||
sourceRevisionDigest: sha256:08108f43d4fba1406b4c8f624792054965c95a14819f442262663cb25ce6cc25
|
||||
sourceBlobDigest: sha256:47fc5915e6a9ff29fca019515d6491adce926407ebb47cee480feb77cfb68f03
|
||||
sourceRevisionDigest: sha256:c71a8e6b169e2ba8a81840f6ebeeb268ee09a440fb16b891f74fe2a9b065b989
|
||||
sourceBlobDigest: sha256:9d925b089f27563fa71967c94b8307007161626a685b84f4c4ab046b78b33f01
|
||||
codeSamplesNamespace: open-router-python-code-samples
|
||||
codeSamplesRevisionDigest: sha256:3c7b0aef799130660fd4017ab9113e6fd3e06a80cff6a540043b9b34dc22facf
|
||||
codeSamplesRevisionDigest: sha256:ad463b22c9ef7c281c59200fc59405a2d57b37cb07a848f6fad47870777c8ec0
|
||||
workflow:
|
||||
workflowVersion: 1.0.0
|
||||
speakeasyVersion: 1.680.0
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
# OpenRouter Python SDK
|
||||
|
||||
The OpenRouter Python SDK is a type-safe toolkit for building AI applications with access to 300+ language models through a unified API.
|
||||
The OpenRouter Python SDK is a type-safe toolkit for building AI applications with access to 400+ language models through a unified API.
|
||||
|
||||
## Why use the OpenRouter SDK?
|
||||
|
||||
|
||||
+35
-8
@@ -1,6 +1,6 @@
|
||||
# OpenRouter SDK (Beta)
|
||||
# OpenRouter SDK
|
||||
|
||||
The [OpenRouter SDK](https://openrouter.ai/docs/sdks/python) is a Python toolkit designed to help you build AI-powered features and solutions. Giving you easy access to over 300 models across providers in an easy and type-safe way.
|
||||
The [OpenRouter SDK](https://openrouter.ai/docs/sdks/python) is a Python toolkit designed to help you build AI-powered features and solutions. Giving you easy access to 400+ models across providers in an easy and type-safe way.
|
||||
|
||||
To learn more about how to use the OpenRouter SDK, check out our [API Reference](https://openrouter.ai/docs/sdks/python/reference) and [Documentation](https://openrouter.ai/docs/sdks/python).
|
||||
|
||||
@@ -199,6 +199,39 @@ with OpenRouter(
|
||||
```
|
||||
<!-- End Pagination [pagination] -->
|
||||
|
||||
<!-- Start File uploads [file-upload] -->
|
||||
## File uploads
|
||||
|
||||
Certain SDK methods accept file objects as part of a request body or multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.
|
||||
|
||||
> [!TIP]
|
||||
>
|
||||
> For endpoints that handle file uploads bytes arrays can also be used. However, using streams is recommended for large files.
|
||||
>
|
||||
|
||||
```python
|
||||
from openrouter import OpenRouter
|
||||
import os
|
||||
|
||||
|
||||
with OpenRouter(
|
||||
http_referer="<value>",
|
||||
x_open_router_title="<value>",
|
||||
x_open_router_categories="<value>",
|
||||
api_key=os.getenv("OPENROUTER_API_KEY", ""),
|
||||
) as open_router:
|
||||
|
||||
res = open_router.files.upload(file={
|
||||
"file_name": "example.file",
|
||||
"content": open("example.file", "rb"),
|
||||
})
|
||||
|
||||
# Handle response
|
||||
print(res)
|
||||
|
||||
```
|
||||
<!-- End File uploads [file-upload] -->
|
||||
|
||||
<!-- Start Resource Management [resource-management] -->
|
||||
## Resource Management
|
||||
|
||||
@@ -277,9 +310,3 @@ To run the test suite, you'll need to set up your environment with an OpenRouter
|
||||
```bash
|
||||
pytest
|
||||
```
|
||||
|
||||
## Maturity
|
||||
|
||||
This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage
|
||||
to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally
|
||||
looking for the latest version.
|
||||
@@ -1,6 +1,6 @@
|
||||
# OpenRouter SDK (Beta)
|
||||
# OpenRouter SDK
|
||||
|
||||
The [OpenRouter SDK](https://openrouter.ai/docs/sdks/python) is a Python toolkit designed to help you build AI-powered features and solutions. Giving you easy access to over 300 models across providers in an easy and type-safe way.
|
||||
The [OpenRouter SDK](https://openrouter.ai/docs/sdks/python) is a Python toolkit designed to help you build AI-powered features and solutions. Giving you easy access to 400+ models across providers in an easy and type-safe way.
|
||||
|
||||
To learn more about how to use the OpenRouter SDK, check out our [API Reference](https://openrouter.ai/docs/sdks/python/reference) and [Documentation](https://openrouter.ai/docs/sdks/python).
|
||||
|
||||
@@ -199,6 +199,39 @@ with OpenRouter(
|
||||
```
|
||||
<!-- End Pagination [pagination] -->
|
||||
|
||||
<!-- Start File uploads [file-upload] -->
|
||||
## File uploads
|
||||
|
||||
Certain SDK methods accept file objects as part of a request body or multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.
|
||||
|
||||
> [!TIP]
|
||||
>
|
||||
> For endpoints that handle file uploads bytes arrays can also be used. However, using streams is recommended for large files.
|
||||
>
|
||||
|
||||
```python
|
||||
from openrouter import OpenRouter
|
||||
import os
|
||||
|
||||
|
||||
with OpenRouter(
|
||||
http_referer="<value>",
|
||||
x_open_router_title="<value>",
|
||||
x_open_router_categories="<value>",
|
||||
api_key=os.getenv("OPENROUTER_API_KEY", ""),
|
||||
) as open_router:
|
||||
|
||||
res = open_router.files.upload(file={
|
||||
"file_name": "example.file",
|
||||
"content": open("example.file", "rb"),
|
||||
})
|
||||
|
||||
# Handle response
|
||||
print(res)
|
||||
|
||||
```
|
||||
<!-- End File uploads [file-upload] -->
|
||||
|
||||
<!-- Start Resource Management [resource-management] -->
|
||||
## Resource Management
|
||||
|
||||
@@ -277,9 +310,3 @@ To run the test suite, you'll need to set up your environment with an OpenRouter
|
||||
```bash
|
||||
pytest
|
||||
```
|
||||
|
||||
## Maturity
|
||||
|
||||
This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage
|
||||
to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally
|
||||
looking for the latest version.
|
||||
+70
@@ -19,3 +19,73 @@ Based on:
|
||||
- [python v0.9.2] .
|
||||
### Releases
|
||||
- [PyPI v0.9.2] https://pypi.org/project/openrouter/0.9.2 - .
|
||||
|
||||
## 2026-06-17 00:59:07
|
||||
### Changes
|
||||
Based on:
|
||||
- OpenAPI Doc
|
||||
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
|
||||
### Generated
|
||||
- [python v0.10.0] .
|
||||
### Releases
|
||||
- [PyPI v0.10.0] https://pypi.org/project/openrouter/0.10.0 - .
|
||||
|
||||
## 2026-06-25 21:56:51
|
||||
### Changes
|
||||
Based on:
|
||||
- OpenAPI Doc
|
||||
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
|
||||
### Generated
|
||||
- [python v0.10.1] .
|
||||
### Releases
|
||||
- [PyPI v0.10.1] https://pypi.org/project/openrouter/0.10.1 - .
|
||||
|
||||
## 2026-06-25 22:28:38
|
||||
### Changes
|
||||
Based on:
|
||||
- OpenAPI Doc
|
||||
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
|
||||
### Generated
|
||||
- [python v0.10.2] .
|
||||
### Releases
|
||||
- [PyPI v0.10.2] https://pypi.org/project/openrouter/0.10.2 - .
|
||||
|
||||
## 2026-06-26 00:15:50
|
||||
### Changes
|
||||
Based on:
|
||||
- OpenAPI Doc
|
||||
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
|
||||
### Generated
|
||||
- [python v0.10.3] .
|
||||
### Releases
|
||||
- [PyPI v0.10.3] https://pypi.org/project/openrouter/0.10.3 - .
|
||||
|
||||
## 2026-06-26 12:06:01
|
||||
### Changes
|
||||
Based on:
|
||||
- OpenAPI Doc
|
||||
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
|
||||
### Generated
|
||||
- [python v0.10.4] .
|
||||
### Releases
|
||||
- [PyPI v0.10.4] https://pypi.org/project/openrouter/0.10.4 - .
|
||||
|
||||
## 2026-06-26 14:36:56
|
||||
### Changes
|
||||
Based on:
|
||||
- OpenAPI Doc
|
||||
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
|
||||
### Generated
|
||||
- [python v0.10.5] .
|
||||
### Releases
|
||||
- [PyPI v0.10.5] https://pypi.org/project/openrouter/0.10.5 - .
|
||||
|
||||
## 2026-06-26 18:19:11
|
||||
### Changes
|
||||
Based on:
|
||||
- OpenAPI Doc
|
||||
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
|
||||
### Generated
|
||||
- [python v0.10.6] .
|
||||
### Releases
|
||||
- [PyPI v0.10.6] https://pypi.org/project/openrouter/0.10.6 - .
|
||||
@@ -1,13 +0,0 @@
|
||||
# CompletionTokensDetails
|
||||
|
||||
Detailed completion token usage
|
||||
|
||||
|
||||
## Fields
|
||||
|
||||
| Field | Type | Required | Description |
|
||||
| ---------------------------- | ---------------------------- | ---------------------------- | ---------------------------- |
|
||||
| `accepted_prediction_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Accepted prediction tokens |
|
||||
| `audio_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Tokens used for audio output |
|
||||
| `reasoning_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Tokens used for reasoning |
|
||||
| `rejected_prediction_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Rejected prediction tokens |
|
||||
@@ -1,11 +0,0 @@
|
||||
# Error
|
||||
|
||||
Error information
|
||||
|
||||
|
||||
## Fields
|
||||
|
||||
| Field | Type | Required | Description | Example |
|
||||
| ------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
|
||||
| `code` | *int* | :heavy_check_mark: | Error code | 429 |
|
||||
| `message` | *str* | :heavy_check_mark: | Error message | Rate limit exceeded |
|
||||
+21
-19
@@ -5,22 +5,24 @@ Information about an AI model available on OpenRouter
|
||||
|
||||
## Fields
|
||||
|
||||
| Field | Type | Required | Description | Example |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `architecture` | [components.ModelArchitecture](../components/modelarchitecture.md) | :heavy_check_mark: | Model architecture information | {<br/>"input_modalities": [<br/>"text"<br/>],<br/>"instruct_type": "chatml",<br/>"modality": "text-\u003etext",<br/>"output_modalities": [<br/>"text"<br/>],<br/>"tokenizer": "GPT"<br/>} |
|
||||
| `canonical_slug` | *str* | :heavy_check_mark: | Canonical slug for the model | openai/gpt-4 |
|
||||
| `context_length` | *Nullable[int]* | :heavy_check_mark: | Maximum context length in tokens | 8192 |
|
||||
| `created` | *int* | :heavy_check_mark: | Unix timestamp of when the model was created | 1692901234 |
|
||||
| `default_parameters` | [Nullable[components.DefaultParameters]](../components/defaultparameters.md) | :heavy_check_mark: | Default parameters for this model | {<br/>"frequency_penalty": 0,<br/>"presence_penalty": 0,<br/>"repetition_penalty": 1,<br/>"temperature": 0.7,<br/>"top_k": 0,<br/>"top_p": 0.9<br/>} |
|
||||
| `description` | *Optional[str]* | :heavy_minus_sign: | Description of the model | GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy. |
|
||||
| `expiration_date` | *OptionalNullable[str]* | :heavy_minus_sign: | The date after which the model may be removed. ISO 8601 date string (YYYY-MM-DD) or null if no expiration. | 2025-06-01 |
|
||||
| `hugging_face_id` | *OptionalNullable[str]* | :heavy_minus_sign: | Hugging Face model identifier, if applicable | microsoft/DialoGPT-medium |
|
||||
| `id` | *str* | :heavy_check_mark: | Unique identifier for the model | openai/gpt-4 |
|
||||
| `knowledge_cutoff` | *OptionalNullable[str]* | :heavy_minus_sign: | The date up to which the model was trained on data. ISO 8601 date string (YYYY-MM-DD) or null if unknown. | 2024-10-01 |
|
||||
| `links` | [components.ModelLinks](../components/modellinks.md) | :heavy_check_mark: | Related API endpoints and resources for this model. | {<br/>"details": "/api/v1/models/openai/gpt-5.4/endpoints"<br/>} |
|
||||
| `name` | *str* | :heavy_check_mark: | Display name of the model | GPT-4 |
|
||||
| `per_request_limits` | [Nullable[components.PerRequestLimits]](../components/perrequestlimits.md) | :heavy_check_mark: | Per-request token limits | {<br/>"completion_tokens": 1000,<br/>"prompt_tokens": 1000<br/>} |
|
||||
| `pricing` | [components.PublicPricing](../components/publicpricing.md) | :heavy_check_mark: | Pricing information for the model | {<br/>"completion": "0.00006",<br/>"image": "0",<br/>"prompt": "0.00003",<br/>"request": "0"<br/>} |
|
||||
| `supported_parameters` | List[[components.Parameter](../components/parameter.md)] | :heavy_check_mark: | List of supported parameters for this model | |
|
||||
| `supported_voices` | List[*str*] | :heavy_check_mark: | List of supported voice identifiers for TTS models. Null for non-TTS models. | <nil> |
|
||||
| `top_provider` | [components.TopProviderInfo](../components/topproviderinfo.md) | :heavy_check_mark: | Information about the top provider for this model | {<br/>"context_length": 8192,<br/>"is_moderated": true,<br/>"max_completion_tokens": 4096<br/>} |
|
||||
| Field | Type | Required | Description | Example |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `architecture` | [components.ModelArchitecture](../components/modelarchitecture.md) | :heavy_check_mark: | Model architecture information | {<br/>"input_modalities": [<br/>"text"<br/>],<br/>"instruct_type": "chatml",<br/>"modality": "text-\u003etext",<br/>"output_modalities": [<br/>"text"<br/>],<br/>"tokenizer": "GPT"<br/>} |
|
||||
| `benchmarks` | [Optional[components.ModelBenchmarks]](../components/modelbenchmarks.md) | :heavy_minus_sign: | Third-party benchmark rankings for this model. Omitted when no benchmark data is available. | {<br/>"artificial_analysis": {<br/>"agentic_index": 55.8,<br/>"coding_index": 63.2,<br/>"intelligence_index": 71.4<br/>},<br/>"design_arena": [<br/>{<br/>"arena": "models",<br/>"category": "website",<br/>"elo": 1385.2,<br/>"rank": 5,<br/>"win_rate": 62.5<br/>}<br/>]<br/>} |
|
||||
| `canonical_slug` | *str* | :heavy_check_mark: | Canonical slug for the model | openai/gpt-4 |
|
||||
| `context_length` | *Nullable[int]* | :heavy_check_mark: | Maximum context length in tokens | 8192 |
|
||||
| `created` | *int* | :heavy_check_mark: | Unix timestamp of when the model was created | 1692901234 |
|
||||
| `default_parameters` | [Nullable[components.DefaultParameters]](../components/defaultparameters.md) | :heavy_check_mark: | Default parameters for this model | {<br/>"frequency_penalty": 0,<br/>"presence_penalty": 0,<br/>"repetition_penalty": 1,<br/>"temperature": 0.7,<br/>"top_k": 0,<br/>"top_p": 0.9<br/>} |
|
||||
| `description` | *Optional[str]* | :heavy_minus_sign: | Description of the model | GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy. |
|
||||
| `expiration_date` | *OptionalNullable[str]* | :heavy_minus_sign: | The date after which the model may be removed. ISO 8601 date string (YYYY-MM-DD) or null if no expiration. | 2025-06-01 |
|
||||
| `hugging_face_id` | *OptionalNullable[str]* | :heavy_minus_sign: | Hugging Face model identifier, if applicable | microsoft/DialoGPT-medium |
|
||||
| `id` | *str* | :heavy_check_mark: | Unique identifier for the model | openai/gpt-4 |
|
||||
| `knowledge_cutoff` | *OptionalNullable[str]* | :heavy_minus_sign: | The date up to which the model was trained on data. ISO 8601 date string (YYYY-MM-DD) or null if unknown. | 2024-10-01 |
|
||||
| `links` | [components.ModelLinks](../components/modellinks.md) | :heavy_check_mark: | Related API endpoints and resources for this model. | {<br/>"details": "/api/v1/models/openai/gpt-5.4/endpoints"<br/>} |
|
||||
| `name` | *str* | :heavy_check_mark: | Display name of the model | GPT-4 |
|
||||
| `per_request_limits` | [Nullable[components.PerRequestLimits]](../components/perrequestlimits.md) | :heavy_check_mark: | Per-request token limits | {<br/>"completion_tokens": 1000,<br/>"prompt_tokens": 1000<br/>} |
|
||||
| `pricing` | [components.PublicPricing](../components/publicpricing.md) | :heavy_check_mark: | Pricing information for the model | {<br/>"completion": "0.00006",<br/>"image": "0",<br/>"prompt": "0.00003",<br/>"request": "0"<br/>} |
|
||||
| `reasoning` | [Optional[components.ModelReasoning]](../components/modelreasoning.md) | :heavy_minus_sign: | Reasoning effort configuration. Omitted for non-reasoning models and dynamic router models. | {<br/>"default_effort": "medium",<br/>"default_enabled": true,<br/>"mandatory": false,<br/>"supported_efforts": [<br/>"high",<br/>"medium",<br/>"low",<br/>"minimal"<br/>]<br/>} |
|
||||
| `supported_parameters` | List[[components.Parameter](../components/parameter.md)] | :heavy_check_mark: | List of supported parameters for this model | |
|
||||
| `supported_voices` | List[*str*] | :heavy_check_mark: | List of supported voice identifiers for TTS models. Null for non-TTS models. | <nil> |
|
||||
| `top_provider` | [components.TopProviderInfo](../components/topproviderinfo.md) | :heavy_check_mark: | Information about the top provider for this model | {<br/>"context_length": 8192,<br/>"is_moderated": true,<br/>"max_completion_tokens": 4096<br/>} |
|
||||
+17
-16
@@ -3,19 +3,20 @@
|
||||
|
||||
## Fields
|
||||
|
||||
| Field | Type | Required | Description | Example |
|
||||
| -------------------- | -------------------- | -------------------- | -------------------- | -------------------- |
|
||||
| `audio` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `audio_output` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `completion` | *str* | :heavy_check_mark: | N/A | 1000 |
|
||||
| `discount` | *Optional[float]* | :heavy_minus_sign: | N/A | |
|
||||
| `image` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `image_output` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `image_token` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `input_audio_cache` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `input_cache_read` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `input_cache_write` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `internal_reasoning` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `prompt` | *str* | :heavy_check_mark: | N/A | 1000 |
|
||||
| `request` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `web_search` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| Field | Type | Required | Description |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `audio` | *Optional[str]* | :heavy_minus_sign: | Price in USD per audio input token |
|
||||
| `audio_output` | *Optional[str]* | :heavy_minus_sign: | Price in USD per audio output token |
|
||||
| `completion` | *str* | :heavy_check_mark: | Price in USD per token for completion (output) generation |
|
||||
| `discount` | *Optional[float]* | :heavy_minus_sign: | Fractional discount applied to this endpoint's pricing; the price is multiplied by (1 - discount) (0 = no discount, 1 = free) |
|
||||
| `image` | *Optional[str]* | :heavy_minus_sign: | Price in USD per input image |
|
||||
| `image_output` | *Optional[str]* | :heavy_minus_sign: | Price in USD per output image |
|
||||
| `image_token` | *Optional[str]* | :heavy_minus_sign: | Price in USD per image token |
|
||||
| `input_audio_cache` | *Optional[str]* | :heavy_minus_sign: | Price in USD per cached audio input token |
|
||||
| `input_cache_read` | *Optional[str]* | :heavy_minus_sign: | Price in USD per cached input token (read) |
|
||||
| `input_cache_write` | *Optional[str]* | :heavy_minus_sign: | Price per cache-write token, in USD per token. For providers with multiple cache TTLs (e.g. Anthropic), this is the default (5-minute) cache-write rate. |
|
||||
| `input_cache_write_1h` | *Optional[str]* | :heavy_minus_sign: | Price per 1-hour cache-write token, in USD per token. Only present for providers that price an extended (1-hour) cache TTL separately, such as Anthropic. |
|
||||
| `internal_reasoning` | *Optional[str]* | :heavy_minus_sign: | Price in USD per internal reasoning token |
|
||||
| `prompt` | *str* | :heavy_check_mark: | Price in USD per token for prompt (input) processing |
|
||||
| `request` | *Optional[str]* | :heavy_minus_sign: | Price in USD per request |
|
||||
| `web_search` | *Optional[str]* | :heavy_minus_sign: | Price in USD per web search |
|
||||
@@ -1,13 +0,0 @@
|
||||
# PromptTokensDetails
|
||||
|
||||
Detailed prompt token usage
|
||||
|
||||
|
||||
## Fields
|
||||
|
||||
| Field | Type | Required | Description |
|
||||
| ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
|
||||
| `audio_tokens` | *Optional[int]* | :heavy_minus_sign: | Audio input tokens |
|
||||
| `cache_write_tokens` | *Optional[int]* | :heavy_minus_sign: | Tokens written to cache. Only returned for models with explicit caching and cache write pricing. |
|
||||
| `cached_tokens` | *Optional[int]* | :heavy_minus_sign: | Cached prompt tokens |
|
||||
| `video_tokens` | *Optional[int]* | :heavy_minus_sign: | Video input tokens |
|
||||
@@ -42,12 +42,14 @@
|
||||
| `GOOGLE` | Google |
|
||||
| `GOOGLE_AI_STUDIO` | Google AI Studio |
|
||||
| `GROQ` | Groq |
|
||||
| `HEY_GEN` | HeyGen |
|
||||
| `INCEPTION` | Inception |
|
||||
| `INCEPTRON` | Inceptron |
|
||||
| `INFERENCE_NET` | InferenceNet |
|
||||
| `IONSTREAM` | Ionstream |
|
||||
| `INFERMATIC` | Infermatic |
|
||||
| `IO_NET` | Io Net |
|
||||
| `INFERACT_V_LLM` | Inferact vLLM |
|
||||
| `INFLECTION` | Inflection |
|
||||
| `LIQUID` | Liquid |
|
||||
| `MARA` | Mara |
|
||||
@@ -74,6 +76,7 @@
|
||||
| `RECRAFT` | Recraft |
|
||||
| `REKA` | Reka |
|
||||
| `RELACE` | Relace |
|
||||
| `SAKANA_AI` | Sakana AI |
|
||||
| `SAMBA_NOVA` | SambaNova |
|
||||
| `SEED` | Seed |
|
||||
| `SILICON_FLOW` | SiliconFlow |
|
||||
@@ -82,11 +85,13 @@
|
||||
| `STEALTH` | Stealth |
|
||||
| `STREAM_LAKE` | StreamLake |
|
||||
| `SWITCHPOINT` | Switchpoint |
|
||||
| `TENSTORRENT` | Tenstorrent |
|
||||
| `TOGETHER` | Together |
|
||||
| `UPSTAGE` | Upstage |
|
||||
| `VENICE` | Venice |
|
||||
| `WAFER` | Wafer |
|
||||
| `WAND_B` | WandB |
|
||||
| `QUIVER` | Quiver |
|
||||
| `XIAOMI` | Xiaomi |
|
||||
| `X_AI` | xAI |
|
||||
| `Z_AI` | Z.AI |
|
||||
|
||||
@@ -5,19 +5,20 @@ Pricing information for the model
|
||||
|
||||
## Fields
|
||||
|
||||
| Field | Type | Required | Description | Example |
|
||||
| -------------------- | -------------------- | -------------------- | -------------------- | -------------------- |
|
||||
| `audio` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `audio_output` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `completion` | *str* | :heavy_check_mark: | N/A | 1000 |
|
||||
| `discount` | *Optional[float]* | :heavy_minus_sign: | N/A | |
|
||||
| `image` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `image_output` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `image_token` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `input_audio_cache` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `input_cache_read` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `input_cache_write` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `internal_reasoning` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `prompt` | *str* | :heavy_check_mark: | N/A | 1000 |
|
||||
| `request` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| `web_search` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
|
||||
| Field | Type | Required | Description |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `audio` | *Optional[str]* | :heavy_minus_sign: | Price in USD per audio input token |
|
||||
| `audio_output` | *Optional[str]* | :heavy_minus_sign: | Price in USD per audio output token |
|
||||
| `completion` | *str* | :heavy_check_mark: | Price in USD per token for completion (output) generation |
|
||||
| `discount` | *Optional[float]* | :heavy_minus_sign: | Fractional discount applied to this endpoint's pricing; the price is multiplied by (1 - discount) (0 = no discount, 1 = free) |
|
||||
| `image` | *Optional[str]* | :heavy_minus_sign: | Price in USD per input image |
|
||||
| `image_output` | *Optional[str]* | :heavy_minus_sign: | Price in USD per output image |
|
||||
| `image_token` | *Optional[str]* | :heavy_minus_sign: | Price in USD per image token |
|
||||
| `input_audio_cache` | *Optional[str]* | :heavy_minus_sign: | Price in USD per cached audio input token |
|
||||
| `input_cache_read` | *Optional[str]* | :heavy_minus_sign: | Price in USD per cached input token (read) |
|
||||
| `input_cache_write` | *Optional[str]* | :heavy_minus_sign: | Price per cache-write token, in USD per token. For providers with multiple cache TTLs (e.g. Anthropic), this is the default (5-minute) cache-write rate. |
|
||||
| `input_cache_write_1h` | *Optional[str]* | :heavy_minus_sign: | Price per 1-hour cache-write token, in USD per token. Only present for providers that price an extended (1-hour) cache TTL separately, such as Anthropic. |
|
||||
| `internal_reasoning` | *Optional[str]* | :heavy_minus_sign: | Price in USD per internal reasoning token |
|
||||
| `prompt` | *str* | :heavy_check_mark: | Price in USD per token for prompt (input) processing |
|
||||
| `request` | *Optional[str]* | :heavy_minus_sign: | Price in USD per request |
|
||||
| `web_search` | *Optional[str]* | :heavy_minus_sign: | Price in USD per web search |
|
||||
@@ -5,6 +5,7 @@
|
||||
|
||||
| Field | Type | Required | Description |
|
||||
| -------------------------------------------------------------- | -------------------------------------------------------------- | -------------------------------------------------------------- | -------------------------------------------------------------- |
|
||||
| `content` | *Optional[str]* | :heavy_minus_sign: | N/A |
|
||||
| `end_index` | *int* | :heavy_check_mark: | N/A |
|
||||
| `start_index` | *int* | :heavy_check_mark: | N/A |
|
||||
| `title` | *str* | :heavy_check_mark: | N/A |
|
||||
|
||||
@@ -5,9 +5,10 @@ The search engine to use for web search.
|
||||
|
||||
## Values
|
||||
|
||||
| Name | Value |
|
||||
| ----------- | ----------- |
|
||||
| `NATIVE` | native |
|
||||
| `EXA` | exa |
|
||||
| `FIRECRAWL` | firecrawl |
|
||||
| `PARALLEL` | parallel |
|
||||
| Name | Value |
|
||||
| ------------ | ------------ |
|
||||
| `NATIVE` | native |
|
||||
| `EXA` | exa |
|
||||
| `FIRECRAWL` | firecrawl |
|
||||
| `PARALLEL` | parallel |
|
||||
| `PERPLEXITY` | perplexity |
|
||||
@@ -3,12 +3,13 @@
|
||||
|
||||
## Fields
|
||||
|
||||
| Field | Type | Required | Description | Example |
|
||||
| -------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- |
|
||||
| `callback_url` | *str* | :heavy_check_mark: | The callback URL to redirect to after authorization. Note, only https URLs on ports 443 and 3000 are allowed. | https://myapp.com/auth/callback |
|
||||
| `code_challenge` | *Optional[str]* | :heavy_minus_sign: | PKCE code challenge for enhanced security | E9Melhoa2OwvFrEMTJguCHaoeK1t8URWbuGJSstw-cM |
|
||||
| `code_challenge_method` | [Optional[operations.CreateAuthKeysCodeCodeChallengeMethod]](../operations/createauthkeyscodecodechallengemethod.md) | :heavy_minus_sign: | The method used to generate the code challenge | S256 |
|
||||
| `expires_at` | [date](https://docs.python.org/3/library/datetime.html#date-objects) | :heavy_minus_sign: | Optional expiration time for the API key to be created | 2027-12-31T23:59:59Z |
|
||||
| `key_label` | *Optional[str]* | :heavy_minus_sign: | Optional custom label for the API key. Defaults to the app name if not provided. | My Custom Key |
|
||||
| `limit` | *Optional[float]* | :heavy_minus_sign: | Credit limit for the API key to be created | 100 |
|
||||
| `usage_limit_type` | [Optional[operations.UsageLimitType]](../operations/usagelimittype.md) | :heavy_minus_sign: | Optional credit limit reset interval. When set, the credit limit resets on this interval. | monthly |
|
||||
| Field | Type | Required | Description | Example |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `callback_url` | *str* | :heavy_check_mark: | The callback URL to redirect to after authorization. Supports https URLs and localhost/127.0.0.1 URLs on any port for local CLI tools. | https://myapp.com/auth/callback |
|
||||
| `code_challenge` | *Optional[str]* | :heavy_minus_sign: | PKCE code challenge for enhanced security | E9Melhoa2OwvFrEMTJguCHaoeK1t8URWbuGJSstw-cM |
|
||||
| `code_challenge_method` | [Optional[operations.CreateAuthKeysCodeCodeChallengeMethod]](../operations/createauthkeyscodecodechallengemethod.md) | :heavy_minus_sign: | The method used to generate the code challenge | S256 |
|
||||
| `expires_at` | [date](https://docs.python.org/3/library/datetime.html#date-objects) | :heavy_minus_sign: | Optional expiration time for the API key to be created | 2027-12-31T23:59:59Z |
|
||||
| `key_label` | *Optional[str]* | :heavy_minus_sign: | Optional custom label for the API key. Defaults to the app name if not provided. | My Custom Key |
|
||||
| `limit` | *Optional[float]* | :heavy_minus_sign: | Credit limit for the API key to be created | 100 |
|
||||
| `usage_limit_type` | [Optional[operations.UsageLimitType]](../operations/usagelimittype.md) | :heavy_minus_sign: | Optional credit limit reset interval. When set, the credit limit resets on this interval. | monthly |
|
||||
| `workspace_id` | *Optional[str]* | :heavy_minus_sign: | Optional workspace ID to associate the API key with | |
|
||||
@@ -3,12 +3,23 @@
|
||||
|
||||
## Fields
|
||||
|
||||
| Field | Type | Required | Description | Example |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `http_referer` | *Optional[str]* | :heavy_minus_sign: | The app identifier should be your app's URL and is used as the primary identifier for rankings.<br/>This is used to track API usage per application.<br/> | |
|
||||
| `x_open_router_title` | *Optional[str]* | :heavy_minus_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.<br/> | |
|
||||
| `x_open_router_categories` | *Optional[str]* | :heavy_minus_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.<br/> | |
|
||||
| `category` | [Optional[operations.GetModelsCategory]](../operations/getmodelscategory.md) | :heavy_minus_sign: | Filter models by use case category | programming |
|
||||
| `supported_parameters` | *Optional[str]* | :heavy_minus_sign: | Filter models by supported parameter (comma-separated) | temperature |
|
||||
| `output_modalities` | *Optional[str]* | :heavy_minus_sign: | Filter models by output modality. Accepts a comma-separated list of modalities (text, image, audio, embeddings) or "all" to include all models. Defaults to "text". | text |
|
||||
| `sort` | [Optional[operations.GetModelsSort]](../operations/getmodelssort.md) | :heavy_minus_sign: | Sort the returned models server-side. Prefer this over fetching the full list and sorting client-side. Options: pricing-low-to-high, pricing-high-to-low (average prompt/completion price), context-high-to-low (context length), throughput-high-to-low, latency-low-to-high (recent median performance), most-popular, top-weekly (tokens processed in the last week), newest (creation date). When omitted, the existing default ordering is preserved. | newest |
|
||||
| Field | Type | Required | Description | Example |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| `http_referer` | *Optional[str]* | :heavy_minus_sign: | The app identifier should be your app's URL and is used as the primary identifier for rankings.<br/>This is used to track API usage per application.<br/> | |
|
||||
| `x_open_router_title` | *Optional[str]* | :heavy_minus_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.<br/> | |
|
||||
| `x_open_router_categories` | *Optional[str]* | :heavy_minus_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.<br/> | |
|
||||
| `category` | [Optional[operations.GetModelsCategory]](../operations/getmodelscategory.md) | :heavy_minus_sign: | Filter models by use case category | programming |
|
||||
| `supported_parameters` | *Optional[str]* | :heavy_minus_sign: | Filter models by supported parameter (comma-separated) | temperature |
|
||||
| `output_modalities` | *Optional[str]* | :heavy_minus_sign: | Filter models by output modality. Accepts a comma-separated list of modalities (text, image, audio, embeddings) or "all" to include all models. Defaults to "text". | text |
|
||||
| `sort` | [Optional[operations.GetModelsSort]](../operations/getmodelssort.md) | :heavy_minus_sign: | Sort the returned models server-side. Prefer this over fetching the full list and sorting client-side. Options: pricing-low-to-high, pricing-high-to-low (average prompt/completion price), context-high-to-low (context length), throughput-high-to-low, latency-low-to-high (recent median performance), most-popular, top-weekly (tokens processed in the last week), newest (creation date), intelligence-high-to-low (Artificial Analysis intelligence index), design-arena-elo-high-to-low (best Design Arena ELO across arenas). Models without a score for the chosen benchmark are placed last. When omitted, the existing default ordering is preserved. | newest |
|
||||
| `q` | *Optional[str]* | :heavy_minus_sign: | Free-text search by model name or slug. | gpt-4 |
|
||||
| `input_modalities` | *Optional[str]* | :heavy_minus_sign: | Filter models by input modality. Comma-separated list of: text, image, audio, file. | text,image |
|
||||
| `context` | *Optional[int]* | :heavy_minus_sign: | Minimum context length (tokens). Models with smaller context are excluded. | 128000 |
|
||||
| `min_price` | *OptionalNullable[float]* | :heavy_minus_sign: | Minimum prompt price in $/M tokens. | 0 |
|
||||
| `max_price` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum prompt price in $/M tokens. | 10 |
|
||||
| `arch` | *Optional[str]* | :heavy_minus_sign: | Filter models by architecture/model family (e.g. GPT, Claude, Gemini, Llama). | GPT |
|
||||
| `model_authors` | *Optional[str]* | :heavy_minus_sign: | Filter models by the organization that created the model. Comma-separated list of author slugs. | openai,anthropic |
|
||||
| `providers` | *Optional[str]* | :heavy_minus_sign: | Filter models by hosting provider. Comma-separated list of provider names. | OpenAI,Anthropic |
|
||||
| `distillable` | [Optional[operations.Distillable]](../operations/distillable.md) | :heavy_minus_sign: | Filter by distillation capability. "true" returns only distillable models, "false" excludes them. | true |
|
||||
| `zdr` | [Optional[operations.Zdr]](../operations/zdr.md) | :heavy_minus_sign: | When set to "true", return only models with zero data retention endpoints. | true |
|
||||
| `region` | [Optional[operations.Region]](../operations/region.md) | :heavy_minus_sign: | Filter to models with endpoints in the given data region. Currently only "eu" is supported. | eu |
|
||||
@@ -113,7 +113,7 @@ with OpenRouter(
|
||||
|
||||
## create
|
||||
|
||||
Create a new API key for the authenticated user. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
Create a new API key for the authenticated user. The plaintext `key` is returned only in this response. Treat it as a write-only, sensitive value; it cannot be retrieved later. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
|
||||
### Example Usage
|
||||
|
||||
|
||||
@@ -61,6 +61,7 @@ with OpenRouter(
|
||||
| `max_completion_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Maximum tokens in completion | 100 |
|
||||
| `max_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16. | 100 |
|
||||
| `metadata` | Dict[str, *str*] | :heavy_minus_sign: | Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values) | {<br/>"session_id": "session-456",<br/>"user_id": "user-123"<br/>} |
|
||||
| `min_p` | *OptionalNullable[float]* | :heavy_minus_sign: | Minimum probability threshold relative to the most likely token. Tokens with probability below min_p * (probability of top token) are filtered out. Not all providers support this parameter. | 0.1 |
|
||||
| `modalities` | List[[components.Modality](../../components/modality.md)] | :heavy_minus_sign: | Output modalities for the response. Supported values are "text", "image", and "audio". | [<br/>"text",<br/>"image"<br/>] |
|
||||
| `model` | *Optional[str]* | :heavy_minus_sign: | Model to use for completion | openai/gpt-4 |
|
||||
| `models` | List[*str*] | :heavy_minus_sign: | Models to use for completion | [<br/>"openai/gpt-4",<br/>"openai/gpt-4o"<br/>] |
|
||||
@@ -69,6 +70,8 @@ with OpenRouter(
|
||||
| `presence_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | Presence penalty (-2.0 to 2.0) | 0 |
|
||||
| `provider` | [OptionalNullable[components.ProviderPreferences]](../../components/providerpreferences.md) | :heavy_minus_sign: | When multiple model providers are available, optionally indicate your routing preference. | {<br/>"allow_fallbacks": true<br/>} |
|
||||
| `reasoning` | [Optional[components.ChatRequestReasoning]](../../components/chatrequestreasoning.md) | :heavy_minus_sign: | Configuration options for reasoning models | {<br/>"effort": "medium",<br/>"summary": "concise"<br/>} |
|
||||
| `reasoning_effort` | [OptionalNullable[components.ChatRequestReasoningEffort]](../../components/chatrequestreasoningeffort.md) | :heavy_minus_sign: | Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ. | medium |
|
||||
| `repetition_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | Penalizes tokens based on how much they have already appeared in the text. A value of 1.0 means no penalty. Values above 1.0 penalize repeated tokens more strongly. Not all providers support this parameter. | 1 |
|
||||
| `response_format` | [Optional[components.ResponseFormat]](../../components/responseformat.md) | :heavy_minus_sign: | Response format configuration | {<br/>"type": "json_object"<br/>} |
|
||||
| `seed` | *OptionalNullable[int]* | :heavy_minus_sign: | Random seed for deterministic outputs | 42 |
|
||||
| `service_tier` | [OptionalNullable[components.ChatRequestServiceTier]](../../components/chatrequestservicetier.md) | :heavy_minus_sign: | The service tier to use for processing this request. | auto |
|
||||
@@ -80,6 +83,8 @@ with OpenRouter(
|
||||
| `temperature` | *OptionalNullable[float]* | :heavy_minus_sign: | Sampling temperature (0-2) | 0.7 |
|
||||
| `tool_choice` | [Optional[components.ChatToolChoice]](../../components/chattoolchoice.md) | :heavy_minus_sign: | Tool choice configuration | auto |
|
||||
| `tools` | List[[components.ChatFunctionTool](../../components/chatfunctiontool.md)] | :heavy_minus_sign: | Available tools for function calling | [<br/>{<br/>"function": {<br/>"description": "Get weather",<br/>"name": "get_weather"<br/>},<br/>"type": "function"<br/>}<br/>] |
|
||||
| `top_a` | *OptionalNullable[float]* | :heavy_minus_sign: | Consider only tokens with "sufficiently high" probabilities based on the probability of the most likely token. Not all providers support this parameter. | 0 |
|
||||
| `top_k` | *OptionalNullable[int]* | :heavy_minus_sign: | Limits the model to choose from the top K most likely tokens at each step. A value of 1 means the model will always pick the most likely next token. Not all providers support this parameter. | 40 |
|
||||
| `top_logprobs` | *OptionalNullable[int]* | :heavy_minus_sign: | Number of top log probabilities to return (0-20) | 5 |
|
||||
| `top_p` | *OptionalNullable[float]* | :heavy_minus_sign: | Nucleus sampling parameter (0-1) | 1 |
|
||||
| `trace` | [Optional[components.TraceConfig]](../../components/traceconfig.md) | :heavy_minus_sign: | Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations. | {<br/>"trace_id": "trace-abc123",<br/>"trace_name": "my-app-trace"<br/>} |
|
||||
|
||||
@@ -241,7 +241,7 @@ with OpenRouter(
|
||||
|
||||
## update
|
||||
|
||||
Update an existing guardrail. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
Update an existing guardrail. Collection fields use replace semantics: send the full desired set on every update. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
|
||||
### Example Usage
|
||||
|
||||
@@ -359,7 +359,7 @@ with OpenRouter(
|
||||
|
||||
## bulk_assign_keys
|
||||
|
||||
Assign multiple API keys to a specific guardrail. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
Assign multiple API keys to a specific guardrail. A key may hold at most one guardrail; assigning replaces any existing assignment. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
|
||||
### Example Usage
|
||||
|
||||
|
||||
+71
-10
@@ -6,10 +6,60 @@ Model information endpoints
|
||||
|
||||
### Available Operations
|
||||
|
||||
* [get](#get) - Get a model by its slug
|
||||
* [list](#list) - List all models and their properties
|
||||
* [count](#count) - Get total count of available models
|
||||
* [list_for_user](#list_for_user) - List models filtered by user provider preferences, privacy settings, and guardrails
|
||||
|
||||
## get
|
||||
|
||||
Returns full details for a single model identified by its author and slug (e.g. openai/gpt-4). Supports variant suffixes (e.g. openai/gpt-4:free) and resolves known slug aliases.
|
||||
|
||||
### Example Usage
|
||||
|
||||
<!-- UsageSnippet language="python" operationID="getModel" method="get" path="/model/{author}/{slug}" -->
|
||||
```python
|
||||
from openrouter import OpenRouter
|
||||
import os
|
||||
|
||||
|
||||
with OpenRouter(
|
||||
http_referer="<value>",
|
||||
x_open_router_title="<value>",
|
||||
x_open_router_categories="<value>",
|
||||
api_key=os.getenv("OPENROUTER_API_KEY", ""),
|
||||
) as open_router:
|
||||
|
||||
res = open_router.models.get(author="openai", slug="gpt-4")
|
||||
|
||||
# Handle response
|
||||
print(res)
|
||||
|
||||
```
|
||||
|
||||
### Parameters
|
||||
|
||||
| Parameter | Type | Required | Description | Example |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `author` | *str* | :heavy_check_mark: | The author/organization of the model | openai |
|
||||
| `slug` | *str* | :heavy_check_mark: | The model slug, optionally including a variant suffix (e.g. gpt-4 or gpt-4:free) | gpt-4 |
|
||||
| `http_referer` | *Optional[str]* | :heavy_minus_sign: | The app identifier should be your app's URL and is used as the primary identifier for rankings.<br/>This is used to track API usage per application.<br/> | |
|
||||
| `x_open_router_title` | *Optional[str]* | :heavy_minus_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.<br/> | |
|
||||
| `x_open_router_categories` | *Optional[str]* | :heavy_minus_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.<br/> | |
|
||||
| `retries` | [Optional[utils.RetryConfig]](../../models/utils/retryconfig.md) | :heavy_minus_sign: | Configuration to override the default retry behavior of the client. | |
|
||||
|
||||
### Response
|
||||
|
||||
**[components.ModelResponse](../../components/modelresponse.md)**
|
||||
|
||||
### Errors
|
||||
|
||||
| Error Type | Status Code | Content Type |
|
||||
| ---------------------------------- | ---------------------------------- | ---------------------------------- |
|
||||
| errors.NotFoundResponseError | 404 | application/json |
|
||||
| errors.InternalServerResponseError | 500 | application/json |
|
||||
| errors.OpenRouterDefaultError | 4XX, 5XX | \*/\* |
|
||||
|
||||
## list
|
||||
|
||||
List all models and their properties
|
||||
@@ -38,16 +88,27 @@ with OpenRouter(
|
||||
|
||||
### Parameters
|
||||
|
||||
| Parameter | Type | Required | Description | Example |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `http_referer` | *Optional[str]* | :heavy_minus_sign: | The app identifier should be your app's URL and is used as the primary identifier for rankings.<br/>This is used to track API usage per application.<br/> | |
|
||||
| `x_open_router_title` | *Optional[str]* | :heavy_minus_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.<br/> | |
|
||||
| `x_open_router_categories` | *Optional[str]* | :heavy_minus_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.<br/> | |
|
||||
| `category` | [Optional[operations.GetModelsCategory]](../../operations/getmodelscategory.md) | :heavy_minus_sign: | Filter models by use case category | programming |
|
||||
| `supported_parameters` | *Optional[str]* | :heavy_minus_sign: | Filter models by supported parameter (comma-separated) | temperature |
|
||||
| `output_modalities` | *Optional[str]* | :heavy_minus_sign: | Filter models by output modality. Accepts a comma-separated list of modalities (text, image, audio, embeddings) or "all" to include all models. Defaults to "text". | text |
|
||||
| `sort` | [Optional[operations.GetModelsSort]](../../operations/getmodelssort.md) | :heavy_minus_sign: | Sort the returned models server-side. Prefer this over fetching the full list and sorting client-side. Options: pricing-low-to-high, pricing-high-to-low (average prompt/completion price), context-high-to-low (context length), throughput-high-to-low, latency-low-to-high (recent median performance), most-popular, top-weekly (tokens processed in the last week), newest (creation date). When omitted, the existing default ordering is preserved. | newest |
|
||||
| `retries` | [Optional[utils.RetryConfig]](../../models/utils/retryconfig.md) | :heavy_minus_sign: | Configuration to override the default retry behavior of the client. | |
|
||||
| Parameter | Type | Required | Description | Example |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| `http_referer` | *Optional[str]* | :heavy_minus_sign: | The app identifier should be your app's URL and is used as the primary identifier for rankings.<br/>This is used to track API usage per application.<br/> | |
|
||||
| `x_open_router_title` | *Optional[str]* | :heavy_minus_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.<br/> | |
|
||||
| `x_open_router_categories` | *Optional[str]* | :heavy_minus_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.<br/> | |
|
||||
| `category` | [Optional[operations.GetModelsCategory]](../../operations/getmodelscategory.md) | :heavy_minus_sign: | Filter models by use case category | programming |
|
||||
| `supported_parameters` | *Optional[str]* | :heavy_minus_sign: | Filter models by supported parameter (comma-separated) | temperature |
|
||||
| `output_modalities` | *Optional[str]* | :heavy_minus_sign: | Filter models by output modality. Accepts a comma-separated list of modalities (text, image, audio, embeddings) or "all" to include all models. Defaults to "text". | text |
|
||||
| `sort` | [Optional[operations.GetModelsSort]](../../operations/getmodelssort.md) | :heavy_minus_sign: | Sort the returned models server-side. Prefer this over fetching the full list and sorting client-side. Options: pricing-low-to-high, pricing-high-to-low (average prompt/completion price), context-high-to-low (context length), throughput-high-to-low, latency-low-to-high (recent median performance), most-popular, top-weekly (tokens processed in the last week), newest (creation date), intelligence-high-to-low (Artificial Analysis intelligence index), design-arena-elo-high-to-low (best Design Arena ELO across arenas). Models without a score for the chosen benchmark are placed last. When omitted, the existing default ordering is preserved. | newest |
|
||||
| `q` | *Optional[str]* | :heavy_minus_sign: | Free-text search by model name or slug. | gpt-4 |
|
||||
| `input_modalities` | *Optional[str]* | :heavy_minus_sign: | Filter models by input modality. Comma-separated list of: text, image, audio, file. | text,image |
|
||||
| `context` | *Optional[int]* | :heavy_minus_sign: | Minimum context length (tokens). Models with smaller context are excluded. | 128000 |
|
||||
| `min_price` | *OptionalNullable[float]* | :heavy_minus_sign: | Minimum prompt price in $/M tokens. | 0 |
|
||||
| `max_price` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum prompt price in $/M tokens. | 10 |
|
||||
| `arch` | *Optional[str]* | :heavy_minus_sign: | Filter models by architecture/model family (e.g. GPT, Claude, Gemini, Llama). | GPT |
|
||||
| `model_authors` | *Optional[str]* | :heavy_minus_sign: | Filter models by the organization that created the model. Comma-separated list of author slugs. | openai,anthropic |
|
||||
| `providers` | *Optional[str]* | :heavy_minus_sign: | Filter models by hosting provider. Comma-separated list of provider names. | OpenAI,Anthropic |
|
||||
| `distillable` | [Optional[operations.Distillable]](../../operations/distillable.md) | :heavy_minus_sign: | Filter by distillation capability. "true" returns only distillable models, "false" excludes them. | true |
|
||||
| `zdr` | [Optional[operations.Zdr]](../../operations/zdr.md) | :heavy_minus_sign: | When set to "true", return only models with zero data retention endpoints. | true |
|
||||
| `region` | [Optional[operations.Region]](../../operations/region.md) | :heavy_minus_sign: | Filter to models with endpoints in the given data region. Currently only "eu" is supported. | eu |
|
||||
| `retries` | [Optional[utils.RetryConfig]](../../models/utils/retryconfig.md) | :heavy_minus_sign: | Configuration to override the default retry behavior of the client. | |
|
||||
|
||||
### Response
|
||||
|
||||
|
||||
@@ -90,7 +90,7 @@ with OpenRouter(
|
||||
|
||||
| Parameter | Type | Required | Description | Example |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `callback_url` | *str* | :heavy_check_mark: | The callback URL to redirect to after authorization. Note, only https URLs on ports 443 and 3000 are allowed. | https://myapp.com/auth/callback |
|
||||
| `callback_url` | *str* | :heavy_check_mark: | The callback URL to redirect to after authorization. Supports https URLs and localhost/127.0.0.1 URLs on any port for local CLI tools. | https://myapp.com/auth/callback |
|
||||
| `http_referer` | *Optional[str]* | :heavy_minus_sign: | The app identifier should be your app's URL and is used as the primary identifier for rankings.<br/>This is used to track API usage per application.<br/> | |
|
||||
| `x_open_router_title` | *Optional[str]* | :heavy_minus_sign: | The app display name allows you to customize how your app appears in OpenRouter's dashboard.<br/> | |
|
||||
| `x_open_router_categories` | *Optional[str]* | :heavy_minus_sign: | Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.<br/> | |
|
||||
@@ -100,6 +100,7 @@ with OpenRouter(
|
||||
| `key_label` | *Optional[str]* | :heavy_minus_sign: | Optional custom label for the API key. Defaults to the app name if not provided. | My Custom Key |
|
||||
| `limit` | *Optional[float]* | :heavy_minus_sign: | Credit limit for the API key to be created | 100 |
|
||||
| `usage_limit_type` | [Optional[operations.UsageLimitType]](../../operations/usagelimittype.md) | :heavy_minus_sign: | Optional credit limit reset interval. When set, the credit limit resets on this interval. | monthly |
|
||||
| `workspace_id` | *Optional[str]* | :heavy_minus_sign: | Optional workspace ID to associate the API key with | |
|
||||
| `retries` | [Optional[utils.RetryConfig]](../../models/utils/retryconfig.md) | :heavy_minus_sign: | Configuration to override the default retry behavior of the client. | |
|
||||
|
||||
### Response
|
||||
@@ -112,6 +113,7 @@ with OpenRouter(
|
||||
| ---------------------------------- | ---------------------------------- | ---------------------------------- |
|
||||
| errors.BadRequestResponseError | 400 | application/json |
|
||||
| errors.UnauthorizedResponseError | 401 | application/json |
|
||||
| errors.ForbiddenResponseError | 403 | application/json |
|
||||
| errors.ConflictResponseError | 409 | application/json |
|
||||
| errors.InternalServerResponseError | 500 | application/json |
|
||||
| errors.OpenRouterDefaultError | 4XX, 5XX | \*/\* |
|
||||
@@ -46,6 +46,7 @@ with OpenRouter(
|
||||
| `x_open_router_metadata` | [Optional[components.MetadataLevel]](../../components/metadatalevel.md) | :heavy_minus_sign: | Opt-in to surface routing metadata on the response under `openrouter_metadata`. Defaults to `disabled`. The legacy header `X-OpenRouter-Experimental-Metadata` is also accepted for backward compatibility. | enabled |
|
||||
| `background` | *OptionalNullable[bool]* | :heavy_minus_sign: | N/A | |
|
||||
| `cache_control` | [Optional[components.AnthropicCacheControlDirective]](../../components/anthropiccachecontroldirective.md) | :heavy_minus_sign: | Enable automatic prompt caching. When set at the top level, the system automatically applies cache breakpoints to the last cacheable block in the request. Currently supported for Anthropic Claude models. | {<br/>"type": "ephemeral"<br/>} |
|
||||
| `debug` | [Optional[components.ChatDebugOptions]](../../components/chatdebugoptions.md) | :heavy_minus_sign: | Debug options for inspecting request transformations (streaming only) | {<br/>"echo_upstream_body": true<br/>} |
|
||||
| `frequency_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A | |
|
||||
| `image_config` | Dict[str, [components.ImageConfig](../../components/imageconfig.md)] | :heavy_minus_sign: | Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/guides/overview/multimodal/image-generation for more details. | {<br/>"aspect_ratio": "16:9",<br/>"quality": "high"<br/>} |
|
||||
| `include` | List[[components.ResponseIncludesEnum](../../components/responseincludesenum.md)] | :heavy_minus_sign: | N/A | |
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "openrouter"
|
||||
version = "0.9.2"
|
||||
version = "0.10.6"
|
||||
description = "Official Python Client SDK for OpenRouter."
|
||||
authors = [{ name = "OpenRouter" },]
|
||||
readme = "README-PYPI.md"
|
||||
|
||||
@@ -3,10 +3,10 @@
|
||||
import importlib.metadata
|
||||
|
||||
__title__: str = "openrouter"
|
||||
__version__: str = "0.9.2"
|
||||
__version__: str = "0.10.6"
|
||||
__openapi_doc_version__: str = "1.0.0"
|
||||
__gen_version__: str = "2.788.4"
|
||||
__user_agent__: str = "speakeasy-sdk/python 0.9.2 2.788.4 1.0.0 openrouter"
|
||||
__user_agent__: str = "speakeasy-sdk/python 0.10.6 2.788.4 1.0.0 openrouter"
|
||||
|
||||
try:
|
||||
if __package__ is not None:
|
||||
|
||||
@@ -533,7 +533,7 @@ class APIKeys(BaseSDK):
|
||||
) -> operations.CreateKeysResponse:
|
||||
r"""Create a new API key
|
||||
|
||||
Create a new API key for the authenticated user. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
Create a new API key for the authenticated user. The plaintext `key` is returned only in this response. Treat it as a write-only, sensitive value; it cannot be retrieved later. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
|
||||
:param name: Name for the new API key
|
||||
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
||||
@@ -696,7 +696,7 @@ class APIKeys(BaseSDK):
|
||||
) -> operations.CreateKeysResponse:
|
||||
r"""Create a new API key
|
||||
|
||||
Create a new API key for the authenticated user. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
Create a new API key for the authenticated user. The plaintext `key` is returned only in this response. Treat it as a write-only, sensitive value; it cannot be retrieved later. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
|
||||
:param name: Name for the new API key
|
||||
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
||||
|
||||
@@ -0,0 +1,303 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from .basesdk import BaseSDK
|
||||
from openrouter import components, errors, operations, utils
|
||||
from openrouter._hooks import HookContext
|
||||
from openrouter.types import OptionalNullable, UNSET
|
||||
from openrouter.utils import get_security_from_env
|
||||
from openrouter.utils.unmarshal_json_response import unmarshal_json_response
|
||||
from typing import Any, Mapping, Optional
|
||||
|
||||
|
||||
class Benchmarks(BaseSDK):
|
||||
r"""Benchmarks endpoints"""
|
||||
|
||||
def get_benchmarks(
|
||||
self,
|
||||
*,
|
||||
http_referer: Optional[str] = None,
|
||||
x_open_router_title: Optional[str] = None,
|
||||
x_open_router_categories: Optional[str] = None,
|
||||
source: Optional[operations.Source] = None,
|
||||
task_type: Optional[operations.TaskType] = None,
|
||||
arena: Optional[operations.Arena] = None,
|
||||
category: Optional[str] = None,
|
||||
max_results: Optional[int] = None,
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> components.UnifiedBenchmarksResponse:
|
||||
r"""List Benchmarks
|
||||
|
||||
Unified benchmark endpoint that aggregates scores from multiple benchmark sources (Artificial Analysis, Design Arena). Filter by source to reproduce the exact shapes from the legacy per-source endpoints, or use task_type to find models suited for specific workloads. Authenticate with any valid OpenRouter API key. Rate-limited to 30 requests/minute per key and 500 requests/day per account.
|
||||
|
||||
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
||||
This is used to track API usage per application.
|
||||
|
||||
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
||||
|
||||
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
||||
|
||||
:param source: Benchmark source to query. Determines the shape of the returned items. When omitted, returns results from all sources.
|
||||
:param task_type: Filter results by task type. For Artificial Analysis, maps to the corresponding index. For Design Arena, maps to the matching category.
|
||||
:param arena: Design Arena only: arena to query. Defaults to `models` when source is `design-arena`.
|
||||
:param category: Design Arena only: category within the arena (e.g. `codecategories`, `uicomponent`, `gamedev`, `3d`, `dataviz`, `image`, `video`, `svg`). When omitted, returns all categories.
|
||||
:param max_results: Maximum number of items to return. When omitted, all matching results are returned.
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
base_url = None
|
||||
url_variables = None
|
||||
if timeout_ms is None:
|
||||
timeout_ms = self.sdk_configuration.timeout_ms
|
||||
|
||||
if server_url is not None:
|
||||
base_url = server_url
|
||||
else:
|
||||
base_url = self._get_url(base_url, url_variables)
|
||||
|
||||
request = operations.GetBenchmarksRequest(
|
||||
http_referer=http_referer,
|
||||
x_open_router_title=x_open_router_title,
|
||||
x_open_router_categories=x_open_router_categories,
|
||||
source=source,
|
||||
task_type=task_type,
|
||||
arena=arena,
|
||||
category=category,
|
||||
max_results=max_results,
|
||||
)
|
||||
|
||||
req = self._build_request(
|
||||
method="GET",
|
||||
path="/benchmarks",
|
||||
base_url=base_url,
|
||||
url_variables=url_variables,
|
||||
request=request,
|
||||
request_body_required=False,
|
||||
request_has_path_params=False,
|
||||
request_has_query_params=True,
|
||||
user_agent_header="user-agent",
|
||||
accept_header_value="application/json",
|
||||
http_headers=http_headers,
|
||||
_globals=operations.GetBenchmarksGlobals(
|
||||
http_referer=self.sdk_configuration.globals.http_referer,
|
||||
x_open_router_title=self.sdk_configuration.globals.x_open_router_title,
|
||||
x_open_router_categories=self.sdk_configuration.globals.x_open_router_categories,
|
||||
),
|
||||
security=self.sdk_configuration.security,
|
||||
allow_empty_value=None,
|
||||
timeout_ms=timeout_ms,
|
||||
)
|
||||
|
||||
if retries == UNSET:
|
||||
if self.sdk_configuration.retry_config is not UNSET:
|
||||
retries = self.sdk_configuration.retry_config
|
||||
else:
|
||||
retries = utils.RetryConfig(
|
||||
"backoff", utils.BackoffStrategy(500, 60000, 1.5, 3600000), True
|
||||
)
|
||||
|
||||
retry_config = None
|
||||
if isinstance(retries, utils.RetryConfig):
|
||||
retry_config = (retries, ["5XX"])
|
||||
|
||||
http_res = self.do_request(
|
||||
hook_ctx=HookContext(
|
||||
config=self.sdk_configuration,
|
||||
base_url=base_url or "",
|
||||
operation_id="getBenchmarks",
|
||||
oauth2_scopes=None,
|
||||
security_source=get_security_from_env(
|
||||
self.sdk_configuration.security, components.Security
|
||||
),
|
||||
),
|
||||
request=req,
|
||||
error_status_codes=["400", "401", "429", "4XX", "500", "5XX"],
|
||||
retry_config=retry_config,
|
||||
)
|
||||
|
||||
response_data: Any = None
|
||||
if utils.match_response(http_res, "200", "application/json"):
|
||||
return unmarshal_json_response(
|
||||
components.UnifiedBenchmarksResponse, http_res
|
||||
)
|
||||
if utils.match_response(http_res, "400", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.BadRequestResponseErrorData, http_res
|
||||
)
|
||||
raise errors.BadRequestResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "401", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.UnauthorizedResponseErrorData, http_res
|
||||
)
|
||||
raise errors.UnauthorizedResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "429", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.TooManyRequestsResponseErrorData, http_res
|
||||
)
|
||||
raise errors.TooManyRequestsResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "500", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.InternalServerResponseErrorData, http_res
|
||||
)
|
||||
raise errors.InternalServerResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "4XX", "*"):
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
if utils.match_response(http_res, "5XX", "*"):
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
|
||||
raise errors.OpenRouterDefaultError("Unexpected response received", http_res)
|
||||
|
||||
async def get_benchmarks_async(
|
||||
self,
|
||||
*,
|
||||
http_referer: Optional[str] = None,
|
||||
x_open_router_title: Optional[str] = None,
|
||||
x_open_router_categories: Optional[str] = None,
|
||||
source: Optional[operations.Source] = None,
|
||||
task_type: Optional[operations.TaskType] = None,
|
||||
arena: Optional[operations.Arena] = None,
|
||||
category: Optional[str] = None,
|
||||
max_results: Optional[int] = None,
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> components.UnifiedBenchmarksResponse:
|
||||
r"""List Benchmarks
|
||||
|
||||
Unified benchmark endpoint that aggregates scores from multiple benchmark sources (Artificial Analysis, Design Arena). Filter by source to reproduce the exact shapes from the legacy per-source endpoints, or use task_type to find models suited for specific workloads. Authenticate with any valid OpenRouter API key. Rate-limited to 30 requests/minute per key and 500 requests/day per account.
|
||||
|
||||
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
||||
This is used to track API usage per application.
|
||||
|
||||
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
||||
|
||||
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
||||
|
||||
:param source: Benchmark source to query. Determines the shape of the returned items. When omitted, returns results from all sources.
|
||||
:param task_type: Filter results by task type. For Artificial Analysis, maps to the corresponding index. For Design Arena, maps to the matching category.
|
||||
:param arena: Design Arena only: arena to query. Defaults to `models` when source is `design-arena`.
|
||||
:param category: Design Arena only: category within the arena (e.g. `codecategories`, `uicomponent`, `gamedev`, `3d`, `dataviz`, `image`, `video`, `svg`). When omitted, returns all categories.
|
||||
:param max_results: Maximum number of items to return. When omitted, all matching results are returned.
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
base_url = None
|
||||
url_variables = None
|
||||
if timeout_ms is None:
|
||||
timeout_ms = self.sdk_configuration.timeout_ms
|
||||
|
||||
if server_url is not None:
|
||||
base_url = server_url
|
||||
else:
|
||||
base_url = self._get_url(base_url, url_variables)
|
||||
|
||||
request = operations.GetBenchmarksRequest(
|
||||
http_referer=http_referer,
|
||||
x_open_router_title=x_open_router_title,
|
||||
x_open_router_categories=x_open_router_categories,
|
||||
source=source,
|
||||
task_type=task_type,
|
||||
arena=arena,
|
||||
category=category,
|
||||
max_results=max_results,
|
||||
)
|
||||
|
||||
req = self._build_request_async(
|
||||
method="GET",
|
||||
path="/benchmarks",
|
||||
base_url=base_url,
|
||||
url_variables=url_variables,
|
||||
request=request,
|
||||
request_body_required=False,
|
||||
request_has_path_params=False,
|
||||
request_has_query_params=True,
|
||||
user_agent_header="user-agent",
|
||||
accept_header_value="application/json",
|
||||
http_headers=http_headers,
|
||||
_globals=operations.GetBenchmarksGlobals(
|
||||
http_referer=self.sdk_configuration.globals.http_referer,
|
||||
x_open_router_title=self.sdk_configuration.globals.x_open_router_title,
|
||||
x_open_router_categories=self.sdk_configuration.globals.x_open_router_categories,
|
||||
),
|
||||
security=self.sdk_configuration.security,
|
||||
allow_empty_value=None,
|
||||
timeout_ms=timeout_ms,
|
||||
)
|
||||
|
||||
if retries == UNSET:
|
||||
if self.sdk_configuration.retry_config is not UNSET:
|
||||
retries = self.sdk_configuration.retry_config
|
||||
else:
|
||||
retries = utils.RetryConfig(
|
||||
"backoff", utils.BackoffStrategy(500, 60000, 1.5, 3600000), True
|
||||
)
|
||||
|
||||
retry_config = None
|
||||
if isinstance(retries, utils.RetryConfig):
|
||||
retry_config = (retries, ["5XX"])
|
||||
|
||||
http_res = await self.do_request_async(
|
||||
hook_ctx=HookContext(
|
||||
config=self.sdk_configuration,
|
||||
base_url=base_url or "",
|
||||
operation_id="getBenchmarks",
|
||||
oauth2_scopes=None,
|
||||
security_source=get_security_from_env(
|
||||
self.sdk_configuration.security, components.Security
|
||||
),
|
||||
),
|
||||
request=req,
|
||||
error_status_codes=["400", "401", "429", "4XX", "500", "5XX"],
|
||||
retry_config=retry_config,
|
||||
)
|
||||
|
||||
response_data: Any = None
|
||||
if utils.match_response(http_res, "200", "application/json"):
|
||||
return unmarshal_json_response(
|
||||
components.UnifiedBenchmarksResponse, http_res
|
||||
)
|
||||
if utils.match_response(http_res, "400", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.BadRequestResponseErrorData, http_res
|
||||
)
|
||||
raise errors.BadRequestResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "401", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.UnauthorizedResponseErrorData, http_res
|
||||
)
|
||||
raise errors.UnauthorizedResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "429", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.TooManyRequestsResponseErrorData, http_res
|
||||
)
|
||||
raise errors.TooManyRequestsResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "500", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.InternalServerResponseErrorData, http_res
|
||||
)
|
||||
raise errors.InternalServerResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "4XX", "*"):
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
if utils.match_response(http_res, "5XX", "*"):
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
|
||||
raise errors.OpenRouterDefaultError("Unexpected response received", http_res)
|
||||
@@ -302,7 +302,7 @@ class BetaAnalytics(BaseSDK):
|
||||
:param dimensions:
|
||||
:param filters:
|
||||
:param granularity: Time granularity
|
||||
:param group_limit: Maximum rows per distinct combination of dimensions (ClickHouse LIMIT n BY). When omitted on time-series queries (granularity + dimensions), auto-computed to avoid truncating time windows. Explicit values override the default and may truncate time buckets if set lower than the number of buckets in the range. Ignored when no dimensions are specified.
|
||||
:param group_limit: Maximum rows per distinct combination of dimensions. When omitted on time-series queries (granularity + dimensions), auto-computed to avoid truncating time windows. Explicit values override the default and may truncate time buckets if set lower than the number of buckets in the range. Ignored when no dimensions are specified.
|
||||
:param limit: Maximum total rows returned. Defaults to 1000. On time-series queries with dimensions and no explicit group_limit, the server may raise this to accommodate the expected number of unique time-bucket/dimension combinations.
|
||||
:param order_by:
|
||||
:param time_range:
|
||||
@@ -480,7 +480,7 @@ class BetaAnalytics(BaseSDK):
|
||||
:param dimensions:
|
||||
:param filters:
|
||||
:param granularity: Time granularity
|
||||
:param group_limit: Maximum rows per distinct combination of dimensions (ClickHouse LIMIT n BY). When omitted on time-series queries (granularity + dimensions), auto-computed to avoid truncating time windows. Explicit values override the default and may truncate time buckets if set lower than the number of buckets in the range. Ignored when no dimensions are specified.
|
||||
:param group_limit: Maximum rows per distinct combination of dimensions. When omitted on time-series queries (granularity + dimensions), auto-computed to avoid truncating time windows. Explicit values override the default and may truncate time buckets if set lower than the number of buckets in the range. Ignored when no dimensions are specified.
|
||||
:param limit: Maximum total rows returned. Defaults to 1000. On time-series queries with dimensions and no explicit group_limit, the server may raise this to accommodate the expected number of unique time-bucket/dimension combinations.
|
||||
:param order_by:
|
||||
:param time_range:
|
||||
|
||||
@@ -359,7 +359,7 @@ class Byok(BaseSDK):
|
||||
) -> components.CreateBYOKKeyResponse:
|
||||
r"""Create a BYOK provider credential
|
||||
|
||||
Create a new bring-your-own-key (BYOK) provider credential. The raw key is encrypted at rest and never returned in API responses. Defaults to the authenticated entity's default workspace; use the `workspace_id` body field to scope to a different workspace. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
Create a new bring-your-own-key (BYOK) provider credential. The raw key is encrypted at rest and never returned in API responses. Defaults to the authenticated entity's default workspace; use the `workspace_id` body field to scope to a different workspace. Treat the raw key as write-only; it is never returned after creation. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
|
||||
:param key: The raw provider API key or credential. This value is encrypted at rest and never returned in API responses.
|
||||
:param provider: The upstream provider this credential authenticates against, as a lowercase slug (e.g. `openai`, `anthropic`, `amazon-bedrock`).
|
||||
@@ -520,7 +520,7 @@ class Byok(BaseSDK):
|
||||
) -> components.CreateBYOKKeyResponse:
|
||||
r"""Create a BYOK provider credential
|
||||
|
||||
Create a new bring-your-own-key (BYOK) provider credential. The raw key is encrypted at rest and never returned in API responses. Defaults to the authenticated entity's default workspace; use the `workspace_id` body field to scope to a different workspace. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
Create a new bring-your-own-key (BYOK) provider credential. The raw key is encrypted at rest and never returned in API responses. Defaults to the authenticated entity's default workspace; use the `workspace_id` body field to scope to a different workspace. Treat the raw key as write-only; it is never returned after creation. [Management key](/docs/guides/overview/auth/management-api-keys) required.
|
||||
|
||||
:param key: The raw provider API key or credential. This value is encrypted at rest and never returned in API responses.
|
||||
:param provider: The upstream provider this credential authenticates against, as a lowercase slug (e.g. `openai`, `anthropic`, `amazon-bedrock`).
|
||||
|
||||
@@ -48,6 +48,7 @@ class Chat(BaseSDK):
|
||||
max_completion_tokens: OptionalNullable[int] = UNSET,
|
||||
max_tokens: OptionalNullable[int] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
min_p: OptionalNullable[float] = UNSET,
|
||||
modalities: Optional[List[components.Modality]] = None,
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
@@ -70,6 +71,10 @@ class Chat(BaseSDK):
|
||||
components.ChatRequestReasoningTypedDict,
|
||||
]
|
||||
] = None,
|
||||
reasoning_effort: OptionalNullable[
|
||||
components.ChatRequestReasoningEffort
|
||||
] = UNSET,
|
||||
repetition_penalty: OptionalNullable[float] = UNSET,
|
||||
response_format: Optional[
|
||||
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
||||
] = None,
|
||||
@@ -99,6 +104,8 @@ class Chat(BaseSDK):
|
||||
List[components.ChatFunctionToolTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_a: OptionalNullable[float] = UNSET,
|
||||
top_k: OptionalNullable[int] = UNSET,
|
||||
top_logprobs: OptionalNullable[int] = UNSET,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
trace: Optional[
|
||||
@@ -132,6 +139,7 @@ class Chat(BaseSDK):
|
||||
:param max_completion_tokens: Maximum tokens in completion
|
||||
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
||||
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
||||
:param min_p: Minimum probability threshold relative to the most likely token. Tokens with probability below min_p * (probability of top token) are filtered out. Not all providers support this parameter.
|
||||
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
||||
:param model: Model to use for completion
|
||||
:param models: Models to use for completion
|
||||
@@ -140,6 +148,8 @@ class Chat(BaseSDK):
|
||||
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
||||
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
||||
:param reasoning: Configuration options for reasoning models
|
||||
:param reasoning_effort: Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ.
|
||||
:param repetition_penalty: Penalizes tokens based on how much they have already appeared in the text. A value of 1.0 means no penalty. Values above 1.0 penalize repeated tokens more strongly. Not all providers support this parameter.
|
||||
:param response_format: Response format configuration
|
||||
:param seed: Random seed for deterministic outputs
|
||||
:param service_tier: The service tier to use for processing this request.
|
||||
@@ -151,6 +161,8 @@ class Chat(BaseSDK):
|
||||
:param temperature: Sampling temperature (0-2)
|
||||
:param tool_choice: Tool choice configuration
|
||||
:param tools: Available tools for function calling
|
||||
:param top_a: Consider only tokens with \"sufficiently high\" probabilities based on the probability of the most likely token. Not all providers support this parameter.
|
||||
:param top_k: Limits the model to choose from the top K most likely tokens at each step. A value of 1 means the model will always pick the most likely next token. Not all providers support this parameter.
|
||||
:param top_logprobs: Number of top log probabilities to return (0-20)
|
||||
:param top_p: Nucleus sampling parameter (0-1)
|
||||
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
||||
@@ -194,6 +206,7 @@ class Chat(BaseSDK):
|
||||
max_completion_tokens: OptionalNullable[int] = UNSET,
|
||||
max_tokens: OptionalNullable[int] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
min_p: OptionalNullable[float] = UNSET,
|
||||
modalities: Optional[List[components.Modality]] = None,
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
@@ -216,6 +229,10 @@ class Chat(BaseSDK):
|
||||
components.ChatRequestReasoningTypedDict,
|
||||
]
|
||||
] = None,
|
||||
reasoning_effort: OptionalNullable[
|
||||
components.ChatRequestReasoningEffort
|
||||
] = UNSET,
|
||||
repetition_penalty: OptionalNullable[float] = UNSET,
|
||||
response_format: Optional[
|
||||
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
||||
] = None,
|
||||
@@ -245,6 +262,8 @@ class Chat(BaseSDK):
|
||||
List[components.ChatFunctionToolTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_a: OptionalNullable[float] = UNSET,
|
||||
top_k: OptionalNullable[int] = UNSET,
|
||||
top_logprobs: OptionalNullable[int] = UNSET,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
trace: Optional[
|
||||
@@ -278,6 +297,7 @@ class Chat(BaseSDK):
|
||||
:param max_completion_tokens: Maximum tokens in completion
|
||||
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
||||
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
||||
:param min_p: Minimum probability threshold relative to the most likely token. Tokens with probability below min_p * (probability of top token) are filtered out. Not all providers support this parameter.
|
||||
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
||||
:param model: Model to use for completion
|
||||
:param models: Models to use for completion
|
||||
@@ -286,6 +306,8 @@ class Chat(BaseSDK):
|
||||
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
||||
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
||||
:param reasoning: Configuration options for reasoning models
|
||||
:param reasoning_effort: Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ.
|
||||
:param repetition_penalty: Penalizes tokens based on how much they have already appeared in the text. A value of 1.0 means no penalty. Values above 1.0 penalize repeated tokens more strongly. Not all providers support this parameter.
|
||||
:param response_format: Response format configuration
|
||||
:param seed: Random seed for deterministic outputs
|
||||
:param service_tier: The service tier to use for processing this request.
|
||||
@@ -297,6 +319,8 @@ class Chat(BaseSDK):
|
||||
:param temperature: Sampling temperature (0-2)
|
||||
:param tool_choice: Tool choice configuration
|
||||
:param tools: Available tools for function calling
|
||||
:param top_a: Consider only tokens with \"sufficiently high\" probabilities based on the probability of the most likely token. Not all providers support this parameter.
|
||||
:param top_k: Limits the model to choose from the top K most likely tokens at each step. A value of 1 means the model will always pick the most likely next token. Not all providers support this parameter.
|
||||
:param top_logprobs: Number of top log probabilities to return (0-20)
|
||||
:param top_p: Nucleus sampling parameter (0-1)
|
||||
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
||||
@@ -339,6 +363,7 @@ class Chat(BaseSDK):
|
||||
max_completion_tokens: OptionalNullable[int] = UNSET,
|
||||
max_tokens: OptionalNullable[int] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
min_p: OptionalNullable[float] = UNSET,
|
||||
modalities: Optional[List[components.Modality]] = None,
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
@@ -361,6 +386,10 @@ class Chat(BaseSDK):
|
||||
components.ChatRequestReasoningTypedDict,
|
||||
]
|
||||
] = None,
|
||||
reasoning_effort: OptionalNullable[
|
||||
components.ChatRequestReasoningEffort
|
||||
] = UNSET,
|
||||
repetition_penalty: OptionalNullable[float] = UNSET,
|
||||
response_format: Optional[
|
||||
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
||||
] = None,
|
||||
@@ -390,6 +419,8 @@ class Chat(BaseSDK):
|
||||
List[components.ChatFunctionToolTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_a: OptionalNullable[float] = UNSET,
|
||||
top_k: OptionalNullable[int] = UNSET,
|
||||
top_logprobs: OptionalNullable[int] = UNSET,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
trace: Optional[
|
||||
@@ -423,6 +454,7 @@ class Chat(BaseSDK):
|
||||
:param max_completion_tokens: Maximum tokens in completion
|
||||
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
||||
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
||||
:param min_p: Minimum probability threshold relative to the most likely token. Tokens with probability below min_p * (probability of top token) are filtered out. Not all providers support this parameter.
|
||||
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
||||
:param model: Model to use for completion
|
||||
:param models: Models to use for completion
|
||||
@@ -431,6 +463,8 @@ class Chat(BaseSDK):
|
||||
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
||||
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
||||
:param reasoning: Configuration options for reasoning models
|
||||
:param reasoning_effort: Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ.
|
||||
:param repetition_penalty: Penalizes tokens based on how much they have already appeared in the text. A value of 1.0 means no penalty. Values above 1.0 penalize repeated tokens more strongly. Not all providers support this parameter.
|
||||
:param response_format: Response format configuration
|
||||
:param seed: Random seed for deterministic outputs
|
||||
:param service_tier: The service tier to use for processing this request.
|
||||
@@ -442,6 +476,8 @@ class Chat(BaseSDK):
|
||||
:param temperature: Sampling temperature (0-2)
|
||||
:param tool_choice: Tool choice configuration
|
||||
:param tools: Available tools for function calling
|
||||
:param top_a: Consider only tokens with \"sufficiently high\" probabilities based on the probability of the most likely token. Not all providers support this parameter.
|
||||
:param top_k: Limits the model to choose from the top K most likely tokens at each step. A value of 1 means the model will always pick the most likely next token. Not all providers support this parameter.
|
||||
:param top_logprobs: Number of top log probabilities to return (0-20)
|
||||
:param top_p: Nucleus sampling parameter (0-1)
|
||||
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
||||
@@ -484,6 +520,7 @@ class Chat(BaseSDK):
|
||||
messages, List[components.ChatMessages]
|
||||
),
|
||||
metadata=metadata,
|
||||
min_p=min_p,
|
||||
modalities=modalities,
|
||||
model=model,
|
||||
models=models,
|
||||
@@ -498,6 +535,8 @@ class Chat(BaseSDK):
|
||||
reasoning=utils.get_pydantic_model(
|
||||
reasoning, Optional[components.ChatRequestReasoning]
|
||||
),
|
||||
reasoning_effort=reasoning_effort,
|
||||
repetition_penalty=repetition_penalty,
|
||||
response_format=utils.get_pydantic_model(
|
||||
response_format, Optional[components.ResponseFormat]
|
||||
),
|
||||
@@ -520,6 +559,8 @@ class Chat(BaseSDK):
|
||||
tools=utils.get_pydantic_model(
|
||||
tools, Optional[List[components.ChatFunctionTool]]
|
||||
),
|
||||
top_a=top_a,
|
||||
top_k=top_k,
|
||||
top_logprobs=top_logprobs,
|
||||
top_p=top_p,
|
||||
trace=utils.get_pydantic_model(trace, Optional[components.TraceConfig]),
|
||||
@@ -764,6 +805,7 @@ class Chat(BaseSDK):
|
||||
max_completion_tokens: OptionalNullable[int] = UNSET,
|
||||
max_tokens: OptionalNullable[int] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
min_p: OptionalNullable[float] = UNSET,
|
||||
modalities: Optional[List[components.Modality]] = None,
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
@@ -786,6 +828,10 @@ class Chat(BaseSDK):
|
||||
components.ChatRequestReasoningTypedDict,
|
||||
]
|
||||
] = None,
|
||||
reasoning_effort: OptionalNullable[
|
||||
components.ChatRequestReasoningEffort
|
||||
] = UNSET,
|
||||
repetition_penalty: OptionalNullable[float] = UNSET,
|
||||
response_format: Optional[
|
||||
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
||||
] = None,
|
||||
@@ -815,6 +861,8 @@ class Chat(BaseSDK):
|
||||
List[components.ChatFunctionToolTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_a: OptionalNullable[float] = UNSET,
|
||||
top_k: OptionalNullable[int] = UNSET,
|
||||
top_logprobs: OptionalNullable[int] = UNSET,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
trace: Optional[
|
||||
@@ -848,6 +896,7 @@ class Chat(BaseSDK):
|
||||
:param max_completion_tokens: Maximum tokens in completion
|
||||
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
||||
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
||||
:param min_p: Minimum probability threshold relative to the most likely token. Tokens with probability below min_p * (probability of top token) are filtered out. Not all providers support this parameter.
|
||||
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
||||
:param model: Model to use for completion
|
||||
:param models: Models to use for completion
|
||||
@@ -856,6 +905,8 @@ class Chat(BaseSDK):
|
||||
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
||||
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
||||
:param reasoning: Configuration options for reasoning models
|
||||
:param reasoning_effort: Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ.
|
||||
:param repetition_penalty: Penalizes tokens based on how much they have already appeared in the text. A value of 1.0 means no penalty. Values above 1.0 penalize repeated tokens more strongly. Not all providers support this parameter.
|
||||
:param response_format: Response format configuration
|
||||
:param seed: Random seed for deterministic outputs
|
||||
:param service_tier: The service tier to use for processing this request.
|
||||
@@ -867,6 +918,8 @@ class Chat(BaseSDK):
|
||||
:param temperature: Sampling temperature (0-2)
|
||||
:param tool_choice: Tool choice configuration
|
||||
:param tools: Available tools for function calling
|
||||
:param top_a: Consider only tokens with \"sufficiently high\" probabilities based on the probability of the most likely token. Not all providers support this parameter.
|
||||
:param top_k: Limits the model to choose from the top K most likely tokens at each step. A value of 1 means the model will always pick the most likely next token. Not all providers support this parameter.
|
||||
:param top_logprobs: Number of top log probabilities to return (0-20)
|
||||
:param top_p: Nucleus sampling parameter (0-1)
|
||||
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
||||
@@ -910,6 +963,7 @@ class Chat(BaseSDK):
|
||||
max_completion_tokens: OptionalNullable[int] = UNSET,
|
||||
max_tokens: OptionalNullable[int] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
min_p: OptionalNullable[float] = UNSET,
|
||||
modalities: Optional[List[components.Modality]] = None,
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
@@ -932,6 +986,10 @@ class Chat(BaseSDK):
|
||||
components.ChatRequestReasoningTypedDict,
|
||||
]
|
||||
] = None,
|
||||
reasoning_effort: OptionalNullable[
|
||||
components.ChatRequestReasoningEffort
|
||||
] = UNSET,
|
||||
repetition_penalty: OptionalNullable[float] = UNSET,
|
||||
response_format: Optional[
|
||||
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
||||
] = None,
|
||||
@@ -961,6 +1019,8 @@ class Chat(BaseSDK):
|
||||
List[components.ChatFunctionToolTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_a: OptionalNullable[float] = UNSET,
|
||||
top_k: OptionalNullable[int] = UNSET,
|
||||
top_logprobs: OptionalNullable[int] = UNSET,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
trace: Optional[
|
||||
@@ -994,6 +1054,7 @@ class Chat(BaseSDK):
|
||||
:param max_completion_tokens: Maximum tokens in completion
|
||||
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
||||
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
||||
:param min_p: Minimum probability threshold relative to the most likely token. Tokens with probability below min_p * (probability of top token) are filtered out. Not all providers support this parameter.
|
||||
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
||||
:param model: Model to use for completion
|
||||
:param models: Models to use for completion
|
||||
@@ -1002,6 +1063,8 @@ class Chat(BaseSDK):
|
||||
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
||||
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
||||
:param reasoning: Configuration options for reasoning models
|
||||
:param reasoning_effort: Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ.
|
||||
:param repetition_penalty: Penalizes tokens based on how much they have already appeared in the text. A value of 1.0 means no penalty. Values above 1.0 penalize repeated tokens more strongly. Not all providers support this parameter.
|
||||
:param response_format: Response format configuration
|
||||
:param seed: Random seed for deterministic outputs
|
||||
:param service_tier: The service tier to use for processing this request.
|
||||
@@ -1013,6 +1076,8 @@ class Chat(BaseSDK):
|
||||
:param temperature: Sampling temperature (0-2)
|
||||
:param tool_choice: Tool choice configuration
|
||||
:param tools: Available tools for function calling
|
||||
:param top_a: Consider only tokens with \"sufficiently high\" probabilities based on the probability of the most likely token. Not all providers support this parameter.
|
||||
:param top_k: Limits the model to choose from the top K most likely tokens at each step. A value of 1 means the model will always pick the most likely next token. Not all providers support this parameter.
|
||||
:param top_logprobs: Number of top log probabilities to return (0-20)
|
||||
:param top_p: Nucleus sampling parameter (0-1)
|
||||
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
||||
@@ -1055,6 +1120,7 @@ class Chat(BaseSDK):
|
||||
max_completion_tokens: OptionalNullable[int] = UNSET,
|
||||
max_tokens: OptionalNullable[int] = UNSET,
|
||||
metadata: Optional[Dict[str, str]] = None,
|
||||
min_p: OptionalNullable[float] = UNSET,
|
||||
modalities: Optional[List[components.Modality]] = None,
|
||||
model: Optional[str] = None,
|
||||
models: Optional[List[str]] = None,
|
||||
@@ -1077,6 +1143,10 @@ class Chat(BaseSDK):
|
||||
components.ChatRequestReasoningTypedDict,
|
||||
]
|
||||
] = None,
|
||||
reasoning_effort: OptionalNullable[
|
||||
components.ChatRequestReasoningEffort
|
||||
] = UNSET,
|
||||
repetition_penalty: OptionalNullable[float] = UNSET,
|
||||
response_format: Optional[
|
||||
Union[components.ResponseFormat, components.ResponseFormatTypedDict]
|
||||
] = None,
|
||||
@@ -1106,6 +1176,8 @@ class Chat(BaseSDK):
|
||||
List[components.ChatFunctionToolTypedDict],
|
||||
]
|
||||
] = None,
|
||||
top_a: OptionalNullable[float] = UNSET,
|
||||
top_k: OptionalNullable[int] = UNSET,
|
||||
top_logprobs: OptionalNullable[int] = UNSET,
|
||||
top_p: OptionalNullable[float] = UNSET,
|
||||
trace: Optional[
|
||||
@@ -1139,6 +1211,7 @@ class Chat(BaseSDK):
|
||||
:param max_completion_tokens: Maximum tokens in completion
|
||||
:param max_tokens: Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.
|
||||
:param metadata: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
|
||||
:param min_p: Minimum probability threshold relative to the most likely token. Tokens with probability below min_p * (probability of top token) are filtered out. Not all providers support this parameter.
|
||||
:param modalities: Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\".
|
||||
:param model: Model to use for completion
|
||||
:param models: Models to use for completion
|
||||
@@ -1147,6 +1220,8 @@ class Chat(BaseSDK):
|
||||
:param presence_penalty: Presence penalty (-2.0 to 2.0)
|
||||
:param provider: When multiple model providers are available, optionally indicate your routing preference.
|
||||
:param reasoning: Configuration options for reasoning models
|
||||
:param reasoning_effort: Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ.
|
||||
:param repetition_penalty: Penalizes tokens based on how much they have already appeared in the text. A value of 1.0 means no penalty. Values above 1.0 penalize repeated tokens more strongly. Not all providers support this parameter.
|
||||
:param response_format: Response format configuration
|
||||
:param seed: Random seed for deterministic outputs
|
||||
:param service_tier: The service tier to use for processing this request.
|
||||
@@ -1158,6 +1233,8 @@ class Chat(BaseSDK):
|
||||
:param temperature: Sampling temperature (0-2)
|
||||
:param tool_choice: Tool choice configuration
|
||||
:param tools: Available tools for function calling
|
||||
:param top_a: Consider only tokens with \"sufficiently high\" probabilities based on the probability of the most likely token. Not all providers support this parameter.
|
||||
:param top_k: Limits the model to choose from the top K most likely tokens at each step. A value of 1 means the model will always pick the most likely next token. Not all providers support this parameter.
|
||||
:param top_logprobs: Number of top log probabilities to return (0-20)
|
||||
:param top_p: Nucleus sampling parameter (0-1)
|
||||
:param trace: Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
|
||||
@@ -1200,6 +1277,7 @@ class Chat(BaseSDK):
|
||||
messages, List[components.ChatMessages]
|
||||
),
|
||||
metadata=metadata,
|
||||
min_p=min_p,
|
||||
modalities=modalities,
|
||||
model=model,
|
||||
models=models,
|
||||
@@ -1214,6 +1292,8 @@ class Chat(BaseSDK):
|
||||
reasoning=utils.get_pydantic_model(
|
||||
reasoning, Optional[components.ChatRequestReasoning]
|
||||
),
|
||||
reasoning_effort=reasoning_effort,
|
||||
repetition_penalty=repetition_penalty,
|
||||
response_format=utils.get_pydantic_model(
|
||||
response_format, Optional[components.ResponseFormat]
|
||||
),
|
||||
@@ -1236,6 +1316,8 @@ class Chat(BaseSDK):
|
||||
tools=utils.get_pydantic_model(
|
||||
tools, Optional[List[components.ChatFunctionTool]]
|
||||
),
|
||||
top_a=top_a,
|
||||
top_k=top_k,
|
||||
top_logprobs=top_logprobs,
|
||||
top_p=top_p,
|
||||
trace=utils.get_pydantic_model(trace, Optional[components.TraceConfig]),
|
||||
|
||||
@@ -0,0 +1,315 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from .basesdk import BaseSDK
|
||||
from openrouter import components, errors, operations, utils
|
||||
from openrouter._hooks import HookContext
|
||||
from openrouter.types import OptionalNullable, UNSET
|
||||
from openrouter.utils import get_security_from_env
|
||||
from openrouter.utils.unmarshal_json_response import unmarshal_json_response
|
||||
from typing import Any, Mapping, Optional
|
||||
|
||||
|
||||
class Classifications(BaseSDK):
|
||||
r"""Task classification market-share endpoints"""
|
||||
|
||||
def get_task_classifications(
|
||||
self,
|
||||
*,
|
||||
http_referer: Optional[str] = None,
|
||||
x_open_router_title: Optional[str] = None,
|
||||
x_open_router_categories: Optional[str] = None,
|
||||
window: Optional[operations.Window] = "7d",
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> components.TaskClassificationResponse:
|
||||
r"""Task classification market share
|
||||
|
||||
Returns the market-share breakdown of OpenRouter traffic by task classification
|
||||
(e.g. code generation, web search, summarization) over a trailing time window.
|
||||
|
||||
Each classification reports its share of classified sampled requests (`usage_share`)
|
||||
and classified sampled token volume (`token_share`) as fractions between 0 and 1.
|
||||
The unclassified `other` bucket is excluded. Absolute volumes are not exposed
|
||||
because the underlying data is sampled.
|
||||
|
||||
Each classification also includes a `models` array listing the top models by
|
||||
request volume within that classification, with their within-tag usage and token shares.
|
||||
|
||||
Classifications are grouped into macro-categories (Code, Data, Agent, General)
|
||||
with aggregate shares provided for each.
|
||||
|
||||
Authenticate with any valid OpenRouter API key (same key used for inference).
|
||||
Rate-limited to 30 requests/minute per key and 500 requests/day per account.
|
||||
|
||||
When republishing or quoting this data, cite as:
|
||||
\"Source: OpenRouter (openrouter.ai/rankings), as of {as_of}.\"
|
||||
|
||||
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
||||
This is used to track API usage per application.
|
||||
|
||||
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
||||
|
||||
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
||||
|
||||
:param window: Trailing time window for the classification data. Currently only `7d` (trailing 7 days) is supported.
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
base_url = None
|
||||
url_variables = None
|
||||
if timeout_ms is None:
|
||||
timeout_ms = self.sdk_configuration.timeout_ms
|
||||
|
||||
if server_url is not None:
|
||||
base_url = server_url
|
||||
else:
|
||||
base_url = self._get_url(base_url, url_variables)
|
||||
|
||||
request = operations.GetTaskClassificationsRequest(
|
||||
http_referer=http_referer,
|
||||
x_open_router_title=x_open_router_title,
|
||||
x_open_router_categories=x_open_router_categories,
|
||||
window=window,
|
||||
)
|
||||
|
||||
req = self._build_request(
|
||||
method="GET",
|
||||
path="/classifications/task",
|
||||
base_url=base_url,
|
||||
url_variables=url_variables,
|
||||
request=request,
|
||||
request_body_required=False,
|
||||
request_has_path_params=False,
|
||||
request_has_query_params=True,
|
||||
user_agent_header="user-agent",
|
||||
accept_header_value="application/json",
|
||||
http_headers=http_headers,
|
||||
_globals=operations.GetTaskClassificationsGlobals(
|
||||
http_referer=self.sdk_configuration.globals.http_referer,
|
||||
x_open_router_title=self.sdk_configuration.globals.x_open_router_title,
|
||||
x_open_router_categories=self.sdk_configuration.globals.x_open_router_categories,
|
||||
),
|
||||
security=self.sdk_configuration.security,
|
||||
allow_empty_value=None,
|
||||
timeout_ms=timeout_ms,
|
||||
)
|
||||
|
||||
if retries == UNSET:
|
||||
if self.sdk_configuration.retry_config is not UNSET:
|
||||
retries = self.sdk_configuration.retry_config
|
||||
else:
|
||||
retries = utils.RetryConfig(
|
||||
"backoff", utils.BackoffStrategy(500, 60000, 1.5, 3600000), True
|
||||
)
|
||||
|
||||
retry_config = None
|
||||
if isinstance(retries, utils.RetryConfig):
|
||||
retry_config = (retries, ["5XX"])
|
||||
|
||||
http_res = self.do_request(
|
||||
hook_ctx=HookContext(
|
||||
config=self.sdk_configuration,
|
||||
base_url=base_url or "",
|
||||
operation_id="getTaskClassifications",
|
||||
oauth2_scopes=None,
|
||||
security_source=get_security_from_env(
|
||||
self.sdk_configuration.security, components.Security
|
||||
),
|
||||
),
|
||||
request=req,
|
||||
error_status_codes=["400", "401", "429", "4XX", "500", "5XX"],
|
||||
retry_config=retry_config,
|
||||
)
|
||||
|
||||
response_data: Any = None
|
||||
if utils.match_response(http_res, "200", "application/json"):
|
||||
return unmarshal_json_response(
|
||||
components.TaskClassificationResponse, http_res
|
||||
)
|
||||
if utils.match_response(http_res, "400", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.BadRequestResponseErrorData, http_res
|
||||
)
|
||||
raise errors.BadRequestResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "401", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.UnauthorizedResponseErrorData, http_res
|
||||
)
|
||||
raise errors.UnauthorizedResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "429", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.TooManyRequestsResponseErrorData, http_res
|
||||
)
|
||||
raise errors.TooManyRequestsResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "500", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.InternalServerResponseErrorData, http_res
|
||||
)
|
||||
raise errors.InternalServerResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "4XX", "*"):
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
if utils.match_response(http_res, "5XX", "*"):
|
||||
http_res_text = utils.stream_to_text(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
|
||||
raise errors.OpenRouterDefaultError("Unexpected response received", http_res)
|
||||
|
||||
async def get_task_classifications_async(
|
||||
self,
|
||||
*,
|
||||
http_referer: Optional[str] = None,
|
||||
x_open_router_title: Optional[str] = None,
|
||||
x_open_router_categories: Optional[str] = None,
|
||||
window: Optional[operations.Window] = "7d",
|
||||
retries: OptionalNullable[utils.RetryConfig] = UNSET,
|
||||
server_url: Optional[str] = None,
|
||||
timeout_ms: Optional[int] = None,
|
||||
http_headers: Optional[Mapping[str, str]] = None,
|
||||
) -> components.TaskClassificationResponse:
|
||||
r"""Task classification market share
|
||||
|
||||
Returns the market-share breakdown of OpenRouter traffic by task classification
|
||||
(e.g. code generation, web search, summarization) over a trailing time window.
|
||||
|
||||
Each classification reports its share of classified sampled requests (`usage_share`)
|
||||
and classified sampled token volume (`token_share`) as fractions between 0 and 1.
|
||||
The unclassified `other` bucket is excluded. Absolute volumes are not exposed
|
||||
because the underlying data is sampled.
|
||||
|
||||
Each classification also includes a `models` array listing the top models by
|
||||
request volume within that classification, with their within-tag usage and token shares.
|
||||
|
||||
Classifications are grouped into macro-categories (Code, Data, Agent, General)
|
||||
with aggregate shares provided for each.
|
||||
|
||||
Authenticate with any valid OpenRouter API key (same key used for inference).
|
||||
Rate-limited to 30 requests/minute per key and 500 requests/day per account.
|
||||
|
||||
When republishing or quoting this data, cite as:
|
||||
\"Source: OpenRouter (openrouter.ai/rankings), as of {as_of}.\"
|
||||
|
||||
:param http_referer: The app identifier should be your app's URL and is used as the primary identifier for rankings.
|
||||
This is used to track API usage per application.
|
||||
|
||||
:param x_open_router_title: The app display name allows you to customize how your app appears in OpenRouter's dashboard.
|
||||
|
||||
:param x_open_router_categories: Comma-separated list of app categories (e.g. \"cli-agent,cloud-agent\"). Used for marketplace rankings.
|
||||
|
||||
:param window: Trailing time window for the classification data. Currently only `7d` (trailing 7 days) is supported.
|
||||
:param retries: Override the default retry configuration for this method
|
||||
:param server_url: Override the default server URL for this method
|
||||
:param timeout_ms: Override the default request timeout configuration for this method in milliseconds
|
||||
:param http_headers: Additional headers to set or replace on requests.
|
||||
"""
|
||||
base_url = None
|
||||
url_variables = None
|
||||
if timeout_ms is None:
|
||||
timeout_ms = self.sdk_configuration.timeout_ms
|
||||
|
||||
if server_url is not None:
|
||||
base_url = server_url
|
||||
else:
|
||||
base_url = self._get_url(base_url, url_variables)
|
||||
|
||||
request = operations.GetTaskClassificationsRequest(
|
||||
http_referer=http_referer,
|
||||
x_open_router_title=x_open_router_title,
|
||||
x_open_router_categories=x_open_router_categories,
|
||||
window=window,
|
||||
)
|
||||
|
||||
req = self._build_request_async(
|
||||
method="GET",
|
||||
path="/classifications/task",
|
||||
base_url=base_url,
|
||||
url_variables=url_variables,
|
||||
request=request,
|
||||
request_body_required=False,
|
||||
request_has_path_params=False,
|
||||
request_has_query_params=True,
|
||||
user_agent_header="user-agent",
|
||||
accept_header_value="application/json",
|
||||
http_headers=http_headers,
|
||||
_globals=operations.GetTaskClassificationsGlobals(
|
||||
http_referer=self.sdk_configuration.globals.http_referer,
|
||||
x_open_router_title=self.sdk_configuration.globals.x_open_router_title,
|
||||
x_open_router_categories=self.sdk_configuration.globals.x_open_router_categories,
|
||||
),
|
||||
security=self.sdk_configuration.security,
|
||||
allow_empty_value=None,
|
||||
timeout_ms=timeout_ms,
|
||||
)
|
||||
|
||||
if retries == UNSET:
|
||||
if self.sdk_configuration.retry_config is not UNSET:
|
||||
retries = self.sdk_configuration.retry_config
|
||||
else:
|
||||
retries = utils.RetryConfig(
|
||||
"backoff", utils.BackoffStrategy(500, 60000, 1.5, 3600000), True
|
||||
)
|
||||
|
||||
retry_config = None
|
||||
if isinstance(retries, utils.RetryConfig):
|
||||
retry_config = (retries, ["5XX"])
|
||||
|
||||
http_res = await self.do_request_async(
|
||||
hook_ctx=HookContext(
|
||||
config=self.sdk_configuration,
|
||||
base_url=base_url or "",
|
||||
operation_id="getTaskClassifications",
|
||||
oauth2_scopes=None,
|
||||
security_source=get_security_from_env(
|
||||
self.sdk_configuration.security, components.Security
|
||||
),
|
||||
),
|
||||
request=req,
|
||||
error_status_codes=["400", "401", "429", "4XX", "500", "5XX"],
|
||||
retry_config=retry_config,
|
||||
)
|
||||
|
||||
response_data: Any = None
|
||||
if utils.match_response(http_res, "200", "application/json"):
|
||||
return unmarshal_json_response(
|
||||
components.TaskClassificationResponse, http_res
|
||||
)
|
||||
if utils.match_response(http_res, "400", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.BadRequestResponseErrorData, http_res
|
||||
)
|
||||
raise errors.BadRequestResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "401", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.UnauthorizedResponseErrorData, http_res
|
||||
)
|
||||
raise errors.UnauthorizedResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "429", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.TooManyRequestsResponseErrorData, http_res
|
||||
)
|
||||
raise errors.TooManyRequestsResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "500", "application/json"):
|
||||
response_data = unmarshal_json_response(
|
||||
errors.InternalServerResponseErrorData, http_res
|
||||
)
|
||||
raise errors.InternalServerResponseError(response_data, http_res)
|
||||
if utils.match_response(http_res, "4XX", "*"):
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
if utils.match_response(http_res, "5XX", "*"):
|
||||
http_res_text = await utils.stream_to_text_async(http_res)
|
||||
raise errors.OpenRouterDefaultError(
|
||||
"API error occurred", http_res, http_res_text
|
||||
)
|
||||
|
||||
raise errors.OpenRouterDefaultError("Unexpected response received", http_res)
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,60 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel, Nullable, UNSET_SENTINEL
|
||||
from pydantic import model_serializer
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class AABenchmarkEntryTypedDict(TypedDict):
|
||||
r"""Artificial Analysis benchmark index scores."""
|
||||
|
||||
agentic_index: Nullable[float]
|
||||
r"""Artificial Analysis Agentic Index score"""
|
||||
coding_index: Nullable[float]
|
||||
r"""Artificial Analysis Coding Index score"""
|
||||
intelligence_index: Nullable[float]
|
||||
r"""Artificial Analysis Intelligence Index score"""
|
||||
|
||||
|
||||
class AABenchmarkEntry(BaseModel):
|
||||
r"""Artificial Analysis benchmark index scores."""
|
||||
|
||||
agentic_index: Nullable[float]
|
||||
r"""Artificial Analysis Agentic Index score"""
|
||||
|
||||
coding_index: Nullable[float]
|
||||
r"""Artificial Analysis Coding Index score"""
|
||||
|
||||
intelligence_index: Nullable[float]
|
||||
r"""Artificial Analysis Intelligence Index score"""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = []
|
||||
nullable_fields = ["agentic_index", "coding_index", "intelligence_index"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -9,15 +9,14 @@ from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
class AdvisorNestedToolTypedDict(TypedDict):
|
||||
r"""A tool made available to the advisor sub-agent. Accepts function tools and OpenRouter server tools (e.g. openrouter:web_search). The advisor tool may not list itself."""
|
||||
r"""A tool made available to the advisor sub-agent. Only OpenRouter server tools (e.g. openrouter:web_search) are supported; function tools are rejected because the advisor has no way to execute them. The advisor tool may not list itself."""
|
||||
|
||||
type: str
|
||||
function: NotRequired[Dict[str, Nullable[Any]]]
|
||||
parameters: NotRequired[Dict[str, Nullable[Any]]]
|
||||
|
||||
|
||||
class AdvisorNestedTool(BaseModel):
|
||||
r"""A tool made available to the advisor sub-agent. Accepts function tools and OpenRouter server tools (e.g. openrouter:web_search). The advisor tool may not list itself."""
|
||||
r"""A tool made available to the advisor sub-agent. Only OpenRouter server tools (e.g. openrouter:web_search) are supported; function tools are rejected because the advisor has no way to execute them. The advisor tool may not list itself."""
|
||||
|
||||
model_config = ConfigDict(
|
||||
populate_by_name=True, arbitrary_types_allowed=True, extra="allow"
|
||||
@@ -26,8 +25,6 @@ class AdvisorNestedTool(BaseModel):
|
||||
|
||||
type: str
|
||||
|
||||
function: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
parameters: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
@property
|
||||
|
||||
@@ -10,6 +10,7 @@ from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
AdvisorReasoningEffort = Union[
|
||||
Literal[
|
||||
"max",
|
||||
"xhigh",
|
||||
"high",
|
||||
"medium",
|
||||
|
||||
@@ -30,7 +30,7 @@ class AdvisorServerToolConfigTypedDict(TypedDict):
|
||||
temperature: NotRequired[float]
|
||||
r"""Sampling temperature forwarded to the advisor call. When omitted, the provider's default applies."""
|
||||
tools: NotRequired[List[AdvisorNestedToolTypedDict]]
|
||||
r"""Tools the advisor sub-agent may use while forming its advice. The advisor runs as an agentic sub-agent over these tools, then returns its text. Must not include the advisor tool itself."""
|
||||
r"""Tools the advisor sub-agent may use while forming its advice. The advisor runs as an agentic sub-agent over these tools, then returns its text. Only OpenRouter server tools are supported — function tools are rejected — and the list must not include the advisor tool itself."""
|
||||
|
||||
|
||||
class AdvisorServerToolConfig(BaseModel):
|
||||
@@ -64,4 +64,4 @@ class AdvisorServerToolConfig(BaseModel):
|
||||
r"""Sampling temperature forwarded to the advisor call. When omitted, the provider's default applies."""
|
||||
|
||||
tools: Optional[List[AdvisorNestedTool]] = None
|
||||
r"""Tools the advisor sub-agent may use while forming its advice. The advisor runs as an agentic sub-agent over these tools, then returns its text. Must not include the advisor tool itself."""
|
||||
r"""Tools the advisor sub-agent may use while forming its advice. The advisor runs as an agentic sub-agent over these tools, then returns its text. Only OpenRouter server tools are supported — function tools are rejected — and the list must not include the advisor tool itself."""
|
||||
|
||||
@@ -0,0 +1,82 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .anthropiciterationcachecreation import (
|
||||
AnthropicIterationCacheCreation,
|
||||
AnthropicIterationCacheCreationTypedDict,
|
||||
)
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
)
|
||||
from pydantic import model_serializer
|
||||
from typing import Literal, Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
AnthropicAdvisorMessageUsageIterationType = Literal["advisor_message",]
|
||||
|
||||
|
||||
class AnthropicAdvisorMessageUsageIterationTypedDict(TypedDict):
|
||||
model: str
|
||||
type: AnthropicAdvisorMessageUsageIterationType
|
||||
cache_creation: NotRequired[Nullable[AnthropicIterationCacheCreationTypedDict]]
|
||||
cache_creation_input_tokens: NotRequired[int]
|
||||
cache_read_input_tokens: NotRequired[int]
|
||||
input_tokens: NotRequired[int]
|
||||
output_tokens: NotRequired[int]
|
||||
|
||||
|
||||
class AnthropicAdvisorMessageUsageIteration(BaseModel):
|
||||
model: str
|
||||
|
||||
type: AnthropicAdvisorMessageUsageIterationType
|
||||
|
||||
cache_creation: OptionalNullable[AnthropicIterationCacheCreation] = UNSET
|
||||
|
||||
cache_creation_input_tokens: Optional[int] = None
|
||||
|
||||
cache_read_input_tokens: Optional[int] = None
|
||||
|
||||
input_tokens: Optional[int] = None
|
||||
|
||||
output_tokens: Optional[int] = None
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"cache_creation",
|
||||
"cache_creation_input_tokens",
|
||||
"cache_read_input_tokens",
|
||||
"input_tokens",
|
||||
"output_tokens",
|
||||
]
|
||||
nullable_fields = ["cache_creation"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,79 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .anthropiciterationcachecreation import (
|
||||
AnthropicIterationCacheCreation,
|
||||
AnthropicIterationCacheCreationTypedDict,
|
||||
)
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
)
|
||||
from pydantic import model_serializer
|
||||
from typing import Literal, Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
AnthropicCompactionUsageIterationType = Literal["compaction",]
|
||||
|
||||
|
||||
class AnthropicCompactionUsageIterationTypedDict(TypedDict):
|
||||
type: AnthropicCompactionUsageIterationType
|
||||
cache_creation: NotRequired[Nullable[AnthropicIterationCacheCreationTypedDict]]
|
||||
cache_creation_input_tokens: NotRequired[int]
|
||||
cache_read_input_tokens: NotRequired[int]
|
||||
input_tokens: NotRequired[int]
|
||||
output_tokens: NotRequired[int]
|
||||
|
||||
|
||||
class AnthropicCompactionUsageIteration(BaseModel):
|
||||
type: AnthropicCompactionUsageIterationType
|
||||
|
||||
cache_creation: OptionalNullable[AnthropicIterationCacheCreation] = UNSET
|
||||
|
||||
cache_creation_input_tokens: Optional[int] = None
|
||||
|
||||
cache_read_input_tokens: Optional[int] = None
|
||||
|
||||
input_tokens: Optional[int] = None
|
||||
|
||||
output_tokens: Optional[int] = None
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"cache_creation",
|
||||
"cache_creation_input_tokens",
|
||||
"cache_read_input_tokens",
|
||||
"input_tokens",
|
||||
"output_tokens",
|
||||
]
|
||||
nullable_fields = ["cache_creation"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -9,6 +9,10 @@ from .anthropiccachecontroldirective import (
|
||||
AnthropicCacheControlDirective,
|
||||
AnthropicCacheControlDirectiveTypedDict,
|
||||
)
|
||||
from .anthropicfiledocumentsource import (
|
||||
AnthropicFileDocumentSource,
|
||||
AnthropicFileDocumentSourceTypedDict,
|
||||
)
|
||||
from .anthropicimageblockparam import (
|
||||
AnthropicImageBlockParam,
|
||||
AnthropicImageBlockParamTypedDict,
|
||||
@@ -89,6 +93,7 @@ AnthropicDocumentBlockParamSourceUnionTypedDict = TypeAliasType(
|
||||
Union[
|
||||
SourceContentTypedDict,
|
||||
AnthropicURLPdfSourceTypedDict,
|
||||
AnthropicFileDocumentSourceTypedDict,
|
||||
AnthropicBase64PdfSourceTypedDict,
|
||||
AnthropicPlainTextSourceTypedDict,
|
||||
],
|
||||
@@ -101,6 +106,7 @@ AnthropicDocumentBlockParamSourceUnion = Annotated[
|
||||
Annotated[AnthropicPlainTextSource, Tag("text")],
|
||||
Annotated[SourceContent, Tag("content")],
|
||||
Annotated[AnthropicURLPdfSource, Tag("url")],
|
||||
Annotated[AnthropicFileDocumentSource, Tag("file")],
|
||||
],
|
||||
Discriminator(lambda m: get_discriminator(m, "type", "type")),
|
||||
]
|
||||
|
||||
@@ -0,0 +1,20 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing import Literal
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
AnthropicFileDocumentSourceType = Literal["file",]
|
||||
|
||||
|
||||
class AnthropicFileDocumentSourceTypedDict(TypedDict):
|
||||
file_id: str
|
||||
type: AnthropicFileDocumentSourceType
|
||||
|
||||
|
||||
class AnthropicFileDocumentSource(BaseModel):
|
||||
file_id: str
|
||||
|
||||
type: AnthropicFileDocumentSourceType
|
||||
@@ -0,0 +1,17 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing import Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
class AnthropicIterationCacheCreationTypedDict(TypedDict):
|
||||
ephemeral_1h_input_tokens: NotRequired[int]
|
||||
ephemeral_5m_input_tokens: NotRequired[int]
|
||||
|
||||
|
||||
class AnthropicIterationCacheCreation(BaseModel):
|
||||
ephemeral_1h_input_tokens: Optional[int] = None
|
||||
|
||||
ephemeral_5m_input_tokens: Optional[int] = None
|
||||
@@ -0,0 +1,83 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .anthropiciterationcachecreation import (
|
||||
AnthropicIterationCacheCreation,
|
||||
AnthropicIterationCacheCreationTypedDict,
|
||||
)
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
)
|
||||
from pydantic import model_serializer
|
||||
from typing import Literal, Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
AnthropicMessageUsageIterationType = Literal["message",]
|
||||
|
||||
|
||||
class AnthropicMessageUsageIterationTypedDict(TypedDict):
|
||||
type: AnthropicMessageUsageIterationType
|
||||
cache_creation: NotRequired[Nullable[AnthropicIterationCacheCreationTypedDict]]
|
||||
cache_creation_input_tokens: NotRequired[int]
|
||||
cache_read_input_tokens: NotRequired[int]
|
||||
input_tokens: NotRequired[int]
|
||||
output_tokens: NotRequired[int]
|
||||
model: NotRequired[str]
|
||||
|
||||
|
||||
class AnthropicMessageUsageIteration(BaseModel):
|
||||
type: AnthropicMessageUsageIterationType
|
||||
|
||||
cache_creation: OptionalNullable[AnthropicIterationCacheCreation] = UNSET
|
||||
|
||||
cache_creation_input_tokens: Optional[int] = None
|
||||
|
||||
cache_read_input_tokens: Optional[int] = None
|
||||
|
||||
input_tokens: Optional[int] = None
|
||||
|
||||
output_tokens: Optional[int] = None
|
||||
|
||||
model: Optional[str] = None
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"cache_creation",
|
||||
"cache_creation_input_tokens",
|
||||
"cache_read_input_tokens",
|
||||
"input_tokens",
|
||||
"output_tokens",
|
||||
"model",
|
||||
]
|
||||
nullable_fields = ["cache_creation"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,14 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import UnrecognizedStr
|
||||
from typing import Literal, Union
|
||||
|
||||
|
||||
AnthropicSpeed = Union[
|
||||
Literal[
|
||||
"fast",
|
||||
"standard",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
@@ -0,0 +1,76 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .anthropiciterationcachecreation import (
|
||||
AnthropicIterationCacheCreation,
|
||||
AnthropicIterationCacheCreationTypedDict,
|
||||
)
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
)
|
||||
from pydantic import model_serializer
|
||||
from typing import Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
class AnthropicUnknownUsageIterationTypedDict(TypedDict):
|
||||
type: str
|
||||
cache_creation: NotRequired[Nullable[AnthropicIterationCacheCreationTypedDict]]
|
||||
cache_creation_input_tokens: NotRequired[int]
|
||||
cache_read_input_tokens: NotRequired[int]
|
||||
input_tokens: NotRequired[int]
|
||||
output_tokens: NotRequired[int]
|
||||
|
||||
|
||||
class AnthropicUnknownUsageIteration(BaseModel):
|
||||
type: str
|
||||
|
||||
cache_creation: OptionalNullable[AnthropicIterationCacheCreation] = UNSET
|
||||
|
||||
cache_creation_input_tokens: Optional[int] = None
|
||||
|
||||
cache_read_input_tokens: Optional[int] = None
|
||||
|
||||
input_tokens: Optional[int] = None
|
||||
|
||||
output_tokens: Optional[int] = None
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"cache_creation",
|
||||
"cache_creation_input_tokens",
|
||||
"cache_read_input_tokens",
|
||||
"input_tokens",
|
||||
"output_tokens",
|
||||
]
|
||||
nullable_fields = ["cache_creation"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,43 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .anthropicadvisormessageusageiteration import (
|
||||
AnthropicAdvisorMessageUsageIteration,
|
||||
AnthropicAdvisorMessageUsageIterationTypedDict,
|
||||
)
|
||||
from .anthropiccompactionusageiteration import (
|
||||
AnthropicCompactionUsageIteration,
|
||||
AnthropicCompactionUsageIterationTypedDict,
|
||||
)
|
||||
from .anthropicmessageusageiteration import (
|
||||
AnthropicMessageUsageIteration,
|
||||
AnthropicMessageUsageIterationTypedDict,
|
||||
)
|
||||
from .anthropicunknownusageiteration import (
|
||||
AnthropicUnknownUsageIteration,
|
||||
AnthropicUnknownUsageIterationTypedDict,
|
||||
)
|
||||
from typing import Union
|
||||
from typing_extensions import TypeAliasType
|
||||
|
||||
|
||||
AnthropicUsageIterationTypedDict = TypeAliasType(
|
||||
"AnthropicUsageIterationTypedDict",
|
||||
Union[
|
||||
AnthropicCompactionUsageIterationTypedDict,
|
||||
AnthropicUnknownUsageIterationTypedDict,
|
||||
AnthropicMessageUsageIterationTypedDict,
|
||||
AnthropicAdvisorMessageUsageIterationTypedDict,
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
AnthropicUsageIteration = TypeAliasType(
|
||||
"AnthropicUsageIteration",
|
||||
Union[
|
||||
AnthropicCompactionUsageIteration,
|
||||
AnthropicUnknownUsageIteration,
|
||||
AnthropicMessageUsageIteration,
|
||||
AnthropicAdvisorMessageUsageIteration,
|
||||
],
|
||||
)
|
||||
@@ -0,0 +1,40 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import UnrecognizedStr
|
||||
from typing import Literal, Union
|
||||
|
||||
|
||||
APIErrorType = Union[
|
||||
Literal[
|
||||
"context_length_exceeded",
|
||||
"max_tokens_exceeded",
|
||||
"token_limit_exceeded",
|
||||
"string_too_long",
|
||||
"authentication",
|
||||
"permission_denied",
|
||||
"payment_required",
|
||||
"rate_limit_exceeded",
|
||||
"provider_overloaded",
|
||||
"provider_unavailable",
|
||||
"invalid_request",
|
||||
"invalid_prompt",
|
||||
"not_found",
|
||||
"precondition_failed",
|
||||
"payload_too_large",
|
||||
"unprocessable",
|
||||
"content_policy_violation",
|
||||
"refusal",
|
||||
"invalid_image",
|
||||
"image_too_large",
|
||||
"image_too_small",
|
||||
"unsupported_image_format",
|
||||
"image_not_found",
|
||||
"image_download_failed",
|
||||
"server",
|
||||
"timeout",
|
||||
"unmapped",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""Canonical OpenRouter error type, stable across all API formats"""
|
||||
@@ -0,0 +1,21 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing import Literal
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
BooleanCapabilityType = Literal["boolean",]
|
||||
|
||||
|
||||
class BooleanCapabilityTypedDict(TypedDict):
|
||||
r"""A supported-or-not flag. Present means the parameter is accepted."""
|
||||
|
||||
type: BooleanCapabilityType
|
||||
|
||||
|
||||
class BooleanCapability(BaseModel):
|
||||
r"""A supported-or-not flag. Present means the parameter is accepted."""
|
||||
|
||||
type: BooleanCapabilityType
|
||||
@@ -43,8 +43,10 @@ BYOKProviderSlug = Union[
|
||||
"google-ai-studio",
|
||||
"google-vertex",
|
||||
"groq",
|
||||
"heygen",
|
||||
"inception",
|
||||
"inceptron",
|
||||
"inferact-vllm",
|
||||
"inference-net",
|
||||
"infermatic",
|
||||
"inflection",
|
||||
@@ -72,9 +74,11 @@ BYOKProviderSlug = Union[
|
||||
"perplexity",
|
||||
"phala",
|
||||
"poolside",
|
||||
"quiver",
|
||||
"recraft",
|
||||
"reka",
|
||||
"relace",
|
||||
"sakana-ai",
|
||||
"sambanova",
|
||||
"seed",
|
||||
"siliconflow",
|
||||
@@ -82,6 +86,7 @@ BYOKProviderSlug = Union[
|
||||
"stepfun",
|
||||
"streamlake",
|
||||
"switchpoint",
|
||||
"tenstorrent",
|
||||
"together",
|
||||
"upstage",
|
||||
"venice",
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .booleancapability import BooleanCapability, BooleanCapabilityTypedDict
|
||||
from .enumcapability import EnumCapability, EnumCapabilityTypedDict
|
||||
from .rangecapability import RangeCapability, RangeCapabilityTypedDict
|
||||
from openrouter.utils import get_discriminator
|
||||
from pydantic import Discriminator, Tag
|
||||
from typing import Union
|
||||
from typing_extensions import Annotated, TypeAliasType
|
||||
|
||||
|
||||
CapabilityDescriptorTypedDict = TypeAliasType(
|
||||
"CapabilityDescriptorTypedDict",
|
||||
Union[
|
||||
BooleanCapabilityTypedDict, EnumCapabilityTypedDict, RangeCapabilityTypedDict
|
||||
],
|
||||
)
|
||||
r"""A typed descriptor for one supported request parameter."""
|
||||
|
||||
|
||||
CapabilityDescriptor = Annotated[
|
||||
Union[
|
||||
Annotated[EnumCapability, Tag("enum")],
|
||||
Annotated[RangeCapability, Tag("range")],
|
||||
Annotated[BooleanCapability, Tag("boolean")],
|
||||
],
|
||||
Discriminator(lambda m: get_discriminator(m, "type", "type")),
|
||||
]
|
||||
r"""A typed descriptor for one supported request parameter."""
|
||||
@@ -27,6 +27,10 @@ from .openrouterwebsearchservertool import (
|
||||
OpenRouterWebSearchServerTool,
|
||||
OpenRouterWebSearchServerToolTypedDict,
|
||||
)
|
||||
from .subagentservertool_openrouter import (
|
||||
SubagentServerToolOpenRouter,
|
||||
SubagentServerToolOpenRouterTypedDict,
|
||||
)
|
||||
from .webfetchservertool import WebFetchServerTool, WebFetchServerToolTypedDict
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
@@ -129,6 +133,7 @@ ChatFunctionToolTypedDict = TypeAliasType(
|
||||
DatetimeServerToolTypedDict,
|
||||
ImageGenerationServerToolOpenRouterTypedDict,
|
||||
ChatSearchModelsServerToolTypedDict,
|
||||
SubagentServerToolOpenRouterTypedDict,
|
||||
WebFetchServerToolTypedDict,
|
||||
OpenRouterWebSearchServerToolTypedDict,
|
||||
ChatFunctionToolFunctionTypedDict,
|
||||
@@ -150,6 +155,7 @@ ChatFunctionTool = Annotated[
|
||||
Annotated[
|
||||
ChatSearchModelsServerTool, Tag("openrouter:experimental__search_models")
|
||||
],
|
||||
Annotated[SubagentServerToolOpenRouter, Tag("openrouter:subagent")],
|
||||
Annotated[WebFetchServerTool, Tag("openrouter:web_fetch")],
|
||||
Annotated[OpenRouterWebSearchServerTool, Tag("openrouter:web_search")],
|
||||
Annotated[ChatWebSearchShorthand, Tag("web_search")],
|
||||
|
||||
@@ -106,6 +106,7 @@ ChatRequestPlugin = Annotated[
|
||||
|
||||
ChatRequestEffort = Union[
|
||||
Literal[
|
||||
"max",
|
||||
"xhigh",
|
||||
"high",
|
||||
"medium",
|
||||
@@ -170,6 +171,21 @@ class ChatRequestReasoning(BaseModel):
|
||||
return m
|
||||
|
||||
|
||||
ChatRequestReasoningEffort = Union[
|
||||
Literal[
|
||||
"max",
|
||||
"xhigh",
|
||||
"high",
|
||||
"medium",
|
||||
"low",
|
||||
"minimal",
|
||||
"none",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ."""
|
||||
|
||||
|
||||
ResponseFormatTypedDict = TypeAliasType(
|
||||
"ResponseFormatTypedDict",
|
||||
Union[
|
||||
@@ -240,6 +256,8 @@ class ChatRequestTypedDict(TypedDict):
|
||||
r"""Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16."""
|
||||
metadata: NotRequired[Dict[str, str]]
|
||||
r"""Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)"""
|
||||
min_p: NotRequired[Nullable[float]]
|
||||
r"""Minimum probability threshold relative to the most likely token. Tokens with probability below min_p * (probability of top token) are filtered out. Not all providers support this parameter."""
|
||||
modalities: NotRequired[List[Modality]]
|
||||
r"""Output modalities for the response. Supported values are \"text\", \"image\", and \"audio\"."""
|
||||
model: NotRequired[str]
|
||||
@@ -256,6 +274,10 @@ class ChatRequestTypedDict(TypedDict):
|
||||
r"""When multiple model providers are available, optionally indicate your routing preference."""
|
||||
reasoning: NotRequired[ChatRequestReasoningTypedDict]
|
||||
r"""Configuration options for reasoning models"""
|
||||
reasoning_effort: NotRequired[Nullable[ChatRequestReasoningEffort]]
|
||||
r"""Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ."""
|
||||
repetition_penalty: NotRequired[Nullable[float]]
|
||||
r"""Penalizes tokens based on how much they have already appeared in the text. A value of 1.0 means no penalty. Values above 1.0 penalize repeated tokens more strongly. Not all providers support this parameter."""
|
||||
response_format: NotRequired[ResponseFormatTypedDict]
|
||||
r"""Response format configuration"""
|
||||
seed: NotRequired[Nullable[int]]
|
||||
@@ -278,6 +300,10 @@ class ChatRequestTypedDict(TypedDict):
|
||||
r"""Tool choice configuration"""
|
||||
tools: NotRequired[List[ChatFunctionToolTypedDict]]
|
||||
r"""Available tools for function calling"""
|
||||
top_a: NotRequired[Nullable[float]]
|
||||
r"""Consider only tokens with \"sufficiently high\" probabilities based on the probability of the most likely token. Not all providers support this parameter."""
|
||||
top_k: NotRequired[Nullable[int]]
|
||||
r"""Limits the model to choose from the top K most likely tokens at each step. A value of 1 means the model will always pick the most likely next token. Not all providers support this parameter."""
|
||||
top_logprobs: NotRequired[Nullable[int]]
|
||||
r"""Number of top log probabilities to return (0-20)"""
|
||||
top_p: NotRequired[Nullable[float]]
|
||||
@@ -321,6 +347,9 @@ class ChatRequest(BaseModel):
|
||||
metadata: Optional[Dict[str, str]] = None
|
||||
r"""Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)"""
|
||||
|
||||
min_p: OptionalNullable[float] = UNSET
|
||||
r"""Minimum probability threshold relative to the most likely token. Tokens with probability below min_p * (probability of top token) are filtered out. Not all providers support this parameter."""
|
||||
|
||||
modalities: Optional[
|
||||
List[Annotated[Modality, PlainValidator(validate_open_enum(False))]]
|
||||
] = None
|
||||
@@ -347,6 +376,15 @@ class ChatRequest(BaseModel):
|
||||
reasoning: Optional[ChatRequestReasoning] = None
|
||||
r"""Configuration options for reasoning models"""
|
||||
|
||||
reasoning_effort: Annotated[
|
||||
OptionalNullable[ChatRequestReasoningEffort],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = UNSET
|
||||
r"""Shorthand for setting reasoning effort. Equivalent to setting reasoning.effort. Cannot be used simultaneously with reasoning.effort if they differ."""
|
||||
|
||||
repetition_penalty: OptionalNullable[float] = UNSET
|
||||
r"""Penalizes tokens based on how much they have already appeared in the text. A value of 1.0 means no penalty. Values above 1.0 penalize repeated tokens more strongly. Not all providers support this parameter."""
|
||||
|
||||
response_format: Optional[ResponseFormat] = None
|
||||
r"""Response format configuration"""
|
||||
|
||||
@@ -383,6 +421,12 @@ class ChatRequest(BaseModel):
|
||||
tools: Optional[List[ChatFunctionTool]] = None
|
||||
r"""Available tools for function calling"""
|
||||
|
||||
top_a: OptionalNullable[float] = UNSET
|
||||
r"""Consider only tokens with \"sufficiently high\" probabilities based on the probability of the most likely token. Not all providers support this parameter."""
|
||||
|
||||
top_k: OptionalNullable[int] = UNSET
|
||||
r"""Limits the model to choose from the top K most likely tokens at each step. A value of 1 means the model will always pick the most likely next token. Not all providers support this parameter."""
|
||||
|
||||
top_logprobs: OptionalNullable[int] = UNSET
|
||||
r"""Number of top log probabilities to return (0-20)"""
|
||||
|
||||
@@ -407,6 +451,7 @@ class ChatRequest(BaseModel):
|
||||
"max_completion_tokens",
|
||||
"max_tokens",
|
||||
"metadata",
|
||||
"min_p",
|
||||
"modalities",
|
||||
"model",
|
||||
"models",
|
||||
@@ -415,6 +460,8 @@ class ChatRequest(BaseModel):
|
||||
"presence_penalty",
|
||||
"provider",
|
||||
"reasoning",
|
||||
"reasoning_effort",
|
||||
"repetition_penalty",
|
||||
"response_format",
|
||||
"seed",
|
||||
"service_tier",
|
||||
@@ -426,6 +473,8 @@ class ChatRequest(BaseModel):
|
||||
"temperature",
|
||||
"tool_choice",
|
||||
"tools",
|
||||
"top_a",
|
||||
"top_k",
|
||||
"top_logprobs",
|
||||
"top_p",
|
||||
"trace",
|
||||
@@ -437,14 +486,19 @@ class ChatRequest(BaseModel):
|
||||
"logprobs",
|
||||
"max_completion_tokens",
|
||||
"max_tokens",
|
||||
"min_p",
|
||||
"parallel_tool_calls",
|
||||
"presence_penalty",
|
||||
"provider",
|
||||
"reasoning_effort",
|
||||
"repetition_penalty",
|
||||
"seed",
|
||||
"service_tier",
|
||||
"stop",
|
||||
"stream_options",
|
||||
"temperature",
|
||||
"top_a",
|
||||
"top_k",
|
||||
"top_logprobs",
|
||||
"top_p",
|
||||
]
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .apierrortype import APIErrorType
|
||||
from .chatstreamchoice import ChatStreamChoice, ChatStreamChoiceTypedDict
|
||||
from .chatusage import ChatUsage, ChatUsageTypedDict
|
||||
from .openroutermetadata import OpenRouterMetadata, OpenRouterMetadataTypedDict
|
||||
@@ -11,21 +12,44 @@ from openrouter.types import (
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
)
|
||||
from openrouter.utils import validate_open_enum
|
||||
from pydantic import model_serializer
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import List, Literal, Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
class ErrorTypedDict(TypedDict):
|
||||
class ChatStreamChunkMetadataTypedDict(TypedDict):
|
||||
r"""Structured error metadata"""
|
||||
|
||||
error_type: APIErrorType
|
||||
r"""Canonical OpenRouter error type, stable across all API formats"""
|
||||
provider_code: NotRequired[str]
|
||||
r"""Upstream provider-specific error code, when available"""
|
||||
|
||||
|
||||
class ChatStreamChunkMetadata(BaseModel):
|
||||
r"""Structured error metadata"""
|
||||
|
||||
error_type: Annotated[APIErrorType, PlainValidator(validate_open_enum(False))]
|
||||
r"""Canonical OpenRouter error type, stable across all API formats"""
|
||||
|
||||
provider_code: Optional[str] = None
|
||||
r"""Upstream provider-specific error code, when available"""
|
||||
|
||||
|
||||
class ChatStreamChunkErrorTypedDict(TypedDict):
|
||||
r"""Error information"""
|
||||
|
||||
code: int
|
||||
r"""Error code"""
|
||||
message: str
|
||||
r"""Error message"""
|
||||
metadata: NotRequired[ChatStreamChunkMetadataTypedDict]
|
||||
r"""Structured error metadata"""
|
||||
|
||||
|
||||
class Error(BaseModel):
|
||||
class ChatStreamChunkError(BaseModel):
|
||||
r"""Error information"""
|
||||
|
||||
code: int
|
||||
@@ -34,6 +58,9 @@ class Error(BaseModel):
|
||||
message: str
|
||||
r"""Error message"""
|
||||
|
||||
metadata: Optional[ChatStreamChunkMetadata] = None
|
||||
r"""Structured error metadata"""
|
||||
|
||||
|
||||
ChatStreamChunkObject = Literal["chat.completion.chunk",]
|
||||
|
||||
@@ -50,7 +77,7 @@ class ChatStreamChunkTypedDict(TypedDict):
|
||||
model: str
|
||||
r"""Model used for completion"""
|
||||
object: ChatStreamChunkObject
|
||||
error: NotRequired[ErrorTypedDict]
|
||||
error: NotRequired[ChatStreamChunkErrorTypedDict]
|
||||
r"""Error information"""
|
||||
openrouter_metadata: NotRequired[OpenRouterMetadataTypedDict]
|
||||
service_tier: NotRequired[Nullable[str]]
|
||||
@@ -78,7 +105,7 @@ class ChatStreamChunk(BaseModel):
|
||||
|
||||
object: ChatStreamChunkObject
|
||||
|
||||
error: Optional[Error] = None
|
||||
error: Optional[ChatStreamChunkError] = None
|
||||
r"""Error information"""
|
||||
|
||||
openrouter_metadata: Optional[OpenRouterMetadata] = None
|
||||
|
||||
@@ -14,7 +14,7 @@ from typing import Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
class CompletionTokensDetailsTypedDict(TypedDict):
|
||||
class ChatUsageCompletionTokensDetailsTypedDict(TypedDict):
|
||||
r"""Detailed completion token usage"""
|
||||
|
||||
accepted_prediction_tokens: NotRequired[Nullable[int]]
|
||||
@@ -27,7 +27,7 @@ class CompletionTokensDetailsTypedDict(TypedDict):
|
||||
r"""Rejected prediction tokens"""
|
||||
|
||||
|
||||
class CompletionTokensDetails(BaseModel):
|
||||
class ChatUsageCompletionTokensDetails(BaseModel):
|
||||
r"""Detailed completion token usage"""
|
||||
|
||||
accepted_prediction_tokens: OptionalNullable[int] = UNSET
|
||||
@@ -83,7 +83,7 @@ class CompletionTokensDetails(BaseModel):
|
||||
return m
|
||||
|
||||
|
||||
class PromptTokensDetailsTypedDict(TypedDict):
|
||||
class ChatUsagePromptTokensDetailsTypedDict(TypedDict):
|
||||
r"""Detailed prompt token usage"""
|
||||
|
||||
audio_tokens: NotRequired[int]
|
||||
@@ -96,7 +96,7 @@ class PromptTokensDetailsTypedDict(TypedDict):
|
||||
r"""Video input tokens"""
|
||||
|
||||
|
||||
class PromptTokensDetails(BaseModel):
|
||||
class ChatUsagePromptTokensDetails(BaseModel):
|
||||
r"""Detailed prompt token usage"""
|
||||
|
||||
audio_tokens: Optional[int] = None
|
||||
@@ -112,68 +112,141 @@ class PromptTokensDetails(BaseModel):
|
||||
r"""Video input tokens"""
|
||||
|
||||
|
||||
class ChatUsageTypedDict(TypedDict):
|
||||
r"""Token usage statistics"""
|
||||
class ServerToolUseDetailsTypedDict(TypedDict):
|
||||
r"""Usage for server-side tool execution (e.g., web search)"""
|
||||
|
||||
completion_tokens: int
|
||||
r"""Number of tokens in the completion"""
|
||||
prompt_tokens: int
|
||||
r"""Number of tokens in the prompt"""
|
||||
total_tokens: int
|
||||
r"""Total number of tokens"""
|
||||
completion_tokens_details: NotRequired[Nullable[CompletionTokensDetailsTypedDict]]
|
||||
r"""Detailed completion token usage"""
|
||||
cost: NotRequired[Nullable[float]]
|
||||
r"""Cost of the completion"""
|
||||
cost_details: NotRequired[Nullable[CostDetailsTypedDict]]
|
||||
r"""Breakdown of upstream inference costs"""
|
||||
is_byok: NotRequired[bool]
|
||||
r"""Whether a request was made using a Bring Your Own Key configuration"""
|
||||
prompt_tokens_details: NotRequired[Nullable[PromptTokensDetailsTypedDict]]
|
||||
r"""Detailed prompt token usage"""
|
||||
tool_calls_executed: NotRequired[Nullable[int]]
|
||||
r"""Number of OpenRouter server tool calls that executed and produced a result"""
|
||||
tool_calls_requested: NotRequired[Nullable[int]]
|
||||
r"""Total number of OpenRouter server-orchestrated tool calls the model requested, across all tool types. Provider-native tools (e.g. native web search) are not counted here."""
|
||||
web_search_requests: NotRequired[Nullable[int]]
|
||||
r"""Number of web searches performed by server-side tools. For server-orchestrated tool calls a web search is also counted in tool_calls_requested; provider-native web search may report web_search_requests only. Do not sum the two."""
|
||||
|
||||
|
||||
class ChatUsage(BaseModel):
|
||||
r"""Token usage statistics"""
|
||||
class ServerToolUseDetails(BaseModel):
|
||||
r"""Usage for server-side tool execution (e.g., web search)"""
|
||||
|
||||
completion_tokens: int
|
||||
r"""Number of tokens in the completion"""
|
||||
tool_calls_executed: OptionalNullable[int] = UNSET
|
||||
r"""Number of OpenRouter server tool calls that executed and produced a result"""
|
||||
|
||||
prompt_tokens: int
|
||||
r"""Number of tokens in the prompt"""
|
||||
tool_calls_requested: OptionalNullable[int] = UNSET
|
||||
r"""Total number of OpenRouter server-orchestrated tool calls the model requested, across all tool types. Provider-native tools (e.g. native web search) are not counted here."""
|
||||
|
||||
total_tokens: int
|
||||
r"""Total number of tokens"""
|
||||
|
||||
completion_tokens_details: OptionalNullable[CompletionTokensDetails] = UNSET
|
||||
r"""Detailed completion token usage"""
|
||||
|
||||
cost: OptionalNullable[float] = UNSET
|
||||
r"""Cost of the completion"""
|
||||
|
||||
cost_details: OptionalNullable[CostDetails] = UNSET
|
||||
r"""Breakdown of upstream inference costs"""
|
||||
|
||||
is_byok: Optional[bool] = None
|
||||
r"""Whether a request was made using a Bring Your Own Key configuration"""
|
||||
|
||||
prompt_tokens_details: OptionalNullable[PromptTokensDetails] = UNSET
|
||||
r"""Detailed prompt token usage"""
|
||||
web_search_requests: OptionalNullable[int] = UNSET
|
||||
r"""Number of web searches performed by server-side tools. For server-orchestrated tool calls a web search is also counted in tool_calls_requested; provider-native web search may report web_search_requests only. Do not sum the two."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"completion_tokens_details",
|
||||
"cost",
|
||||
"cost_details",
|
||||
"is_byok",
|
||||
"prompt_tokens_details",
|
||||
"tool_calls_executed",
|
||||
"tool_calls_requested",
|
||||
"web_search_requests",
|
||||
]
|
||||
nullable_fields = [
|
||||
"tool_calls_executed",
|
||||
"tool_calls_requested",
|
||||
"web_search_requests",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
|
||||
|
||||
class ChatUsageTypedDict(TypedDict):
|
||||
r"""Token usage statistics"""
|
||||
|
||||
completion_tokens: int
|
||||
r"""Number of tokens in the completion"""
|
||||
prompt_tokens: int
|
||||
r"""Number of tokens in the prompt"""
|
||||
total_tokens: int
|
||||
r"""Total number of tokens"""
|
||||
completion_tokens_details: NotRequired[
|
||||
Nullable[ChatUsageCompletionTokensDetailsTypedDict]
|
||||
]
|
||||
r"""Detailed completion token usage"""
|
||||
cost: NotRequired[Nullable[float]]
|
||||
r"""Cost of the completion"""
|
||||
cost_details: NotRequired[Nullable[CostDetailsTypedDict]]
|
||||
r"""Breakdown of upstream inference costs"""
|
||||
is_byok: NotRequired[bool]
|
||||
r"""Whether a request was made using a Bring Your Own Key configuration"""
|
||||
prompt_tokens_details: NotRequired[Nullable[ChatUsagePromptTokensDetailsTypedDict]]
|
||||
r"""Detailed prompt token usage"""
|
||||
server_tool_use_details: NotRequired[Nullable[ServerToolUseDetailsTypedDict]]
|
||||
r"""Usage for server-side tool execution (e.g., web search)"""
|
||||
|
||||
|
||||
class ChatUsage(BaseModel):
|
||||
r"""Token usage statistics"""
|
||||
|
||||
completion_tokens: int
|
||||
r"""Number of tokens in the completion"""
|
||||
|
||||
prompt_tokens: int
|
||||
r"""Number of tokens in the prompt"""
|
||||
|
||||
total_tokens: int
|
||||
r"""Total number of tokens"""
|
||||
|
||||
completion_tokens_details: OptionalNullable[ChatUsageCompletionTokensDetails] = (
|
||||
UNSET
|
||||
)
|
||||
r"""Detailed completion token usage"""
|
||||
|
||||
cost: OptionalNullable[float] = UNSET
|
||||
r"""Cost of the completion"""
|
||||
|
||||
cost_details: OptionalNullable[CostDetails] = UNSET
|
||||
r"""Breakdown of upstream inference costs"""
|
||||
|
||||
is_byok: Optional[bool] = None
|
||||
r"""Whether a request was made using a Bring Your Own Key configuration"""
|
||||
|
||||
prompt_tokens_details: OptionalNullable[ChatUsagePromptTokensDetails] = UNSET
|
||||
r"""Detailed prompt token usage"""
|
||||
|
||||
server_tool_use_details: OptionalNullable[ServerToolUseDetails] = UNSET
|
||||
r"""Usage for server-side tool execution (e.g., web search)"""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"completion_tokens_details",
|
||||
"cost",
|
||||
"cost_details",
|
||||
"is_byok",
|
||||
"prompt_tokens_details",
|
||||
"server_tool_use_details",
|
||||
]
|
||||
nullable_fields = [
|
||||
"completion_tokens_details",
|
||||
"cost",
|
||||
"cost_details",
|
||||
"prompt_tokens_details",
|
||||
"server_tool_use_details",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
|
||||
@@ -31,20 +31,20 @@ class ChatWebSearchShorthandTypedDict(TypedDict):
|
||||
|
||||
type: ChatWebSearchShorthandType
|
||||
allowed_domains: NotRequired[List[str]]
|
||||
r"""Limit search results to these domains. Supported by Exa, Firecrawl, Parallel, and most native providers (Anthropic, OpenAI, xAI). Not supported with Perplexity. Cannot be used with excluded_domains."""
|
||||
r"""Limit search results to these domains. Supported by Exa, Firecrawl, Parallel, Perplexity, and most native providers (Anthropic, OpenAI, xAI). Cannot be used with excluded_domains."""
|
||||
engine: NotRequired[WebSearchEngineEnum]
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API."""
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API. \"perplexity\" uses the Perplexity Search API (raw ranked results)."""
|
||||
excluded_domains: NotRequired[List[str]]
|
||||
r"""Exclude search results from these domains. Supported by Exa, Firecrawl, Parallel, Anthropic, and xAI. Not supported with OpenAI (silently ignored) or Perplexity. Cannot be used with allowed_domains."""
|
||||
r"""Exclude search results from these domains. Supported by Exa, Firecrawl, Parallel, Perplexity, Anthropic, and xAI. Not supported with OpenAI (silently ignored). Cannot be used with allowed_domains."""
|
||||
max_characters: NotRequired[int]
|
||||
r"""Exact maximum number of characters of content per search result. Applies to the Exa and Parallel engines; ignored with native provider search and Firecrawl. For Exa, caps highlight content per result. For Parallel, caps excerpt content per result (default 1,500 when omitted). When both `max_characters` and `search_context_size` are set, `max_characters` takes precedence for both engines. When omitted, falls back to `search_context_size` mapping (Exa) or engine defaults (Parallel)."""
|
||||
r"""Exact maximum number of characters of content per search result. Applies to the Exa, Parallel, and Perplexity engines; ignored with native provider search and Firecrawl. For Exa, caps highlight content per result. For Parallel, caps excerpt content per result (default 1,500 when omitted). For Perplexity, maps to the native `max_tokens_per_page` parameter (converted from characters to tokens) and trims the response to the exact character cap. When both `max_characters` and `search_context_size` are set, `max_characters` takes precedence. When omitted, falls back to `search_context_size` mapping (Exa) or engine defaults (Parallel, Perplexity)."""
|
||||
max_results: NotRequired[int]
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, and Parallel engines; ignored with native provider search."""
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, Parallel, and Perplexity engines; ignored with native provider search. Perplexity supports a maximum of 20; values above 20 are clamped."""
|
||||
max_total_results: NotRequired[int]
|
||||
r"""Maximum total number of search results across all search calls in a single request. Once this limit is reached, the tool will stop returning new results. Useful for controlling cost and context size in agentic loops. Defaults to 50 when not specified."""
|
||||
parameters: NotRequired[WebSearchConfigTypedDict]
|
||||
search_context_size: NotRequired[SearchQualityLevel]
|
||||
r"""How much context to retrieve per result. Applies to Exa and Parallel engines; ignored with native provider search and Firecrawl. For Exa, pins a fixed per-result character cap (low=5,000, medium=15,000, high=30,000); when omitted, Exa picks an adaptive size per query and document (typically ~2,000–4,000 characters per result). For Parallel, controls the total characters across all results; when omitted, Parallel uses its own default size. Overridden by `max_characters` when both are set."""
|
||||
r"""How much context to retrieve per result. Applies to Exa, Parallel, and Perplexity engines; ignored with native provider search and Firecrawl. For Exa, pins a fixed per-result character cap (low=5,000, medium=15,000, high=30,000); when omitted, Exa picks an adaptive size per query and document (typically ~2,000–4,000 characters per result). For Parallel, controls the total characters across all results; when omitted, Parallel uses its own default size. For Perplexity, maps directly to the Search API's native search_context_size parameter. Overridden by `max_characters` when both are set."""
|
||||
user_location: NotRequired[WebSearchUserLocationServerToolTypedDict]
|
||||
r"""Approximate user location for location-biased results."""
|
||||
|
||||
@@ -57,21 +57,21 @@ class ChatWebSearchShorthand(BaseModel):
|
||||
]
|
||||
|
||||
allowed_domains: Optional[List[str]] = None
|
||||
r"""Limit search results to these domains. Supported by Exa, Firecrawl, Parallel, and most native providers (Anthropic, OpenAI, xAI). Not supported with Perplexity. Cannot be used with excluded_domains."""
|
||||
r"""Limit search results to these domains. Supported by Exa, Firecrawl, Parallel, Perplexity, and most native providers (Anthropic, OpenAI, xAI). Cannot be used with excluded_domains."""
|
||||
|
||||
engine: Annotated[
|
||||
Optional[WebSearchEngineEnum], PlainValidator(validate_open_enum(False))
|
||||
] = None
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API."""
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API. \"perplexity\" uses the Perplexity Search API (raw ranked results)."""
|
||||
|
||||
excluded_domains: Optional[List[str]] = None
|
||||
r"""Exclude search results from these domains. Supported by Exa, Firecrawl, Parallel, Anthropic, and xAI. Not supported with OpenAI (silently ignored) or Perplexity. Cannot be used with allowed_domains."""
|
||||
r"""Exclude search results from these domains. Supported by Exa, Firecrawl, Parallel, Perplexity, Anthropic, and xAI. Not supported with OpenAI (silently ignored). Cannot be used with allowed_domains."""
|
||||
|
||||
max_characters: Optional[int] = None
|
||||
r"""Exact maximum number of characters of content per search result. Applies to the Exa and Parallel engines; ignored with native provider search and Firecrawl. For Exa, caps highlight content per result. For Parallel, caps excerpt content per result (default 1,500 when omitted). When both `max_characters` and `search_context_size` are set, `max_characters` takes precedence for both engines. When omitted, falls back to `search_context_size` mapping (Exa) or engine defaults (Parallel)."""
|
||||
r"""Exact maximum number of characters of content per search result. Applies to the Exa, Parallel, and Perplexity engines; ignored with native provider search and Firecrawl. For Exa, caps highlight content per result. For Parallel, caps excerpt content per result (default 1,500 when omitted). For Perplexity, maps to the native `max_tokens_per_page` parameter (converted from characters to tokens) and trims the response to the exact character cap. When both `max_characters` and `search_context_size` are set, `max_characters` takes precedence. When omitted, falls back to `search_context_size` mapping (Exa) or engine defaults (Parallel, Perplexity)."""
|
||||
|
||||
max_results: Optional[int] = None
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, and Parallel engines; ignored with native provider search."""
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, Parallel, and Perplexity engines; ignored with native provider search. Perplexity supports a maximum of 20; values above 20 are clamped."""
|
||||
|
||||
max_total_results: Optional[int] = None
|
||||
r"""Maximum total number of search results across all search calls in a single request. Once this limit is reached, the tool will stop returning new results. Useful for controlling cost and context size in agentic loops. Defaults to 50 when not specified."""
|
||||
@@ -81,7 +81,7 @@ class ChatWebSearchShorthand(BaseModel):
|
||||
search_context_size: Annotated[
|
||||
Optional[SearchQualityLevel], PlainValidator(validate_open_enum(False))
|
||||
] = None
|
||||
r"""How much context to retrieve per result. Applies to Exa and Parallel engines; ignored with native provider search and Firecrawl. For Exa, pins a fixed per-result character cap (low=5,000, medium=15,000, high=30,000); when omitted, Exa picks an adaptive size per query and document (typically ~2,000–4,000 characters per result). For Parallel, controls the total characters across all results; when omitted, Parallel uses its own default size. Overridden by `max_characters` when both are set."""
|
||||
r"""How much context to retrieve per result. Applies to Exa, Parallel, and Perplexity engines; ignored with native provider search and Firecrawl. For Exa, pins a fixed per-result character cap (low=5,000, medium=15,000, high=30,000); when omitted, Exa picks an adaptive size per query and document (typically ~2,000–4,000 characters per result). For Parallel, controls the total characters across all results; when omitted, Parallel uses its own default size. For Perplexity, maps directly to the Search API's native search_context_size parameter. Overridden by `max_characters` when both are set."""
|
||||
|
||||
user_location: Optional[WebSearchUserLocationServerTool] = None
|
||||
r"""Approximate user location for location-biased results."""
|
||||
|
||||
@@ -0,0 +1,39 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class DABenchmarkEntryTypedDict(TypedDict):
|
||||
r"""A single Design Arena benchmark entry for a specific arena+category"""
|
||||
|
||||
arena: str
|
||||
r"""Arena type (e.g. models, builders, agents)"""
|
||||
category: str
|
||||
r"""Category within the arena (e.g. website, gamedev, uicomponent)"""
|
||||
elo: float
|
||||
r"""ELO rating from head-to-head arena battles"""
|
||||
rank: int
|
||||
r"""Rank position within this arena+category among models available on OpenRouter (1 = highest ELO)"""
|
||||
win_rate: float
|
||||
r"""Win rate percentage in arena battles"""
|
||||
|
||||
|
||||
class DABenchmarkEntry(BaseModel):
|
||||
r"""A single Design Arena benchmark entry for a specific arena+category"""
|
||||
|
||||
arena: str
|
||||
r"""Arena type (e.g. models, builders, agents)"""
|
||||
|
||||
category: str
|
||||
r"""Category within the arena (e.g. website, gamedev, uicomponent)"""
|
||||
|
||||
elo: float
|
||||
r"""ELO rating from head-to-head arena battles"""
|
||||
|
||||
rank: int
|
||||
r"""Rank position within this arena+category among models available on OpenRouter (1 = highest ELO)"""
|
||||
|
||||
win_rate: float
|
||||
r"""Win rate percentage in arena battles"""
|
||||
@@ -0,0 +1,65 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel, Nullable, UnrecognizedStr
|
||||
from openrouter.utils import validate_open_enum
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import Any, Dict, Literal, Optional, Union
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
Event = Union[
|
||||
Literal[
|
||||
"adapter_request",
|
||||
"upstream_headers_received",
|
||||
"first_token_received",
|
||||
"upstream_body_ended",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
|
||||
|
||||
class TimingsTypedDict(TypedDict):
|
||||
epoch_ms: int
|
||||
event: Event
|
||||
start_ms: int
|
||||
|
||||
|
||||
class Timings(BaseModel):
|
||||
epoch_ms: int
|
||||
|
||||
event: Annotated[Event, PlainValidator(validate_open_enum(False))]
|
||||
|
||||
start_ms: int
|
||||
|
||||
|
||||
class DebugTypedDict(TypedDict):
|
||||
echo_upstream_body: NotRequired[Dict[str, Nullable[Any]]]
|
||||
timings: NotRequired[TimingsTypedDict]
|
||||
|
||||
|
||||
class Debug(BaseModel):
|
||||
echo_upstream_body: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
timings: Optional[Timings] = None
|
||||
|
||||
|
||||
DebugEventType = Literal["response.debug",]
|
||||
|
||||
|
||||
class DebugEventTypedDict(TypedDict):
|
||||
r"""Debug event emitted when debug.echo_upstream_body is true. Contains the transformed upstream request body or timing milestones."""
|
||||
|
||||
debug: DebugTypedDict
|
||||
sequence_number: int
|
||||
type: DebugEventType
|
||||
|
||||
|
||||
class DebugEvent(BaseModel):
|
||||
r"""Debug event emitted when debug.echo_upstream_body is true. Contains the transformed upstream request body or timing milestones."""
|
||||
|
||||
debug: Debug
|
||||
|
||||
sequence_number: int
|
||||
|
||||
type: DebugEventType
|
||||
@@ -0,0 +1,22 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from openrouter.utils import validate_const
|
||||
import pydantic
|
||||
from pydantic.functional_validators import AfterValidator
|
||||
from typing import Literal
|
||||
from typing_extensions import Annotated, TypedDict
|
||||
|
||||
|
||||
class DeleteWorkspaceBudgetResponseTypedDict(TypedDict):
|
||||
deleted: Literal[True]
|
||||
r"""Confirmation that the budget was deleted (or did not exist)"""
|
||||
|
||||
|
||||
class DeleteWorkspaceBudgetResponse(BaseModel):
|
||||
DELETED: Annotated[
|
||||
Annotated[Literal[True], AfterValidator(validate_const(True))],
|
||||
pydantic.Field(alias="deleted"),
|
||||
] = True
|
||||
r"""Confirmation that the budget was deleted (or did not exist)"""
|
||||
@@ -0,0 +1,24 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing import List, Literal
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
EnumCapabilityType = Literal["enum",]
|
||||
|
||||
|
||||
class EnumCapabilityTypedDict(TypedDict):
|
||||
r"""A parameter that accepts one of a discrete set of string values."""
|
||||
|
||||
type: EnumCapabilityType
|
||||
values: List[str]
|
||||
|
||||
|
||||
class EnumCapability(BaseModel):
|
||||
r"""A parameter that accepts one of a discrete set of string values."""
|
||||
|
||||
type: EnumCapabilityType
|
||||
|
||||
values: List[str]
|
||||
@@ -0,0 +1,24 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing import Literal
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
FileDeleteResponseType = Literal["file_deleted",]
|
||||
|
||||
|
||||
class FileDeleteResponseTypedDict(TypedDict):
|
||||
r"""Confirmation that a file was deleted."""
|
||||
|
||||
id: str
|
||||
type: FileDeleteResponseType
|
||||
|
||||
|
||||
class FileDeleteResponse(BaseModel):
|
||||
r"""Confirmation that a file was deleted."""
|
||||
|
||||
id: str
|
||||
|
||||
type: FileDeleteResponseType
|
||||
@@ -0,0 +1,64 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .filemetadata import FileMetadata, FileMetadataTypedDict
|
||||
from openrouter.types import BaseModel, Nullable, UNSET_SENTINEL
|
||||
from pydantic import model_serializer
|
||||
from typing import List
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class FileListResponseTypedDict(TypedDict):
|
||||
r"""A page of files belonging to the requesting workspace."""
|
||||
|
||||
cursor: Nullable[str]
|
||||
r"""Opaque cursor for the next page; null when there are no more results."""
|
||||
data: List[FileMetadataTypedDict]
|
||||
first_id: Nullable[str]
|
||||
has_more: bool
|
||||
last_id: Nullable[str]
|
||||
|
||||
|
||||
class FileListResponse(BaseModel):
|
||||
r"""A page of files belonging to the requesting workspace."""
|
||||
|
||||
cursor: Nullable[str]
|
||||
r"""Opaque cursor for the next page; null when there are no more results."""
|
||||
|
||||
data: List[FileMetadata]
|
||||
|
||||
first_id: Nullable[str]
|
||||
|
||||
has_more: bool
|
||||
|
||||
last_id: Nullable[str]
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = []
|
||||
nullable_fields = ["cursor", "first_id", "last_id"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,39 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing import Literal
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
FileMetadataType = Literal["file",]
|
||||
|
||||
|
||||
class FileMetadataTypedDict(TypedDict):
|
||||
r"""Metadata describing a stored file."""
|
||||
|
||||
created_at: str
|
||||
downloadable: bool
|
||||
filename: str
|
||||
id: str
|
||||
mime_type: str
|
||||
size_bytes: int
|
||||
type: FileMetadataType
|
||||
|
||||
|
||||
class FileMetadata(BaseModel):
|
||||
r"""Metadata describing a stored file."""
|
||||
|
||||
created_at: str
|
||||
|
||||
downloadable: bool
|
||||
|
||||
filename: str
|
||||
|
||||
id: str
|
||||
|
||||
mime_type: str
|
||||
|
||||
size_bytes: int
|
||||
|
||||
type: FileMetadataType
|
||||
@@ -1,14 +1,27 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel, Nullable
|
||||
from typing import Any, Dict, List, Literal, Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
from openrouter.types import BaseModel, Nullable, UnrecognizedStr
|
||||
from openrouter.utils import validate_open_enum
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import Any, Dict, List, Literal, Optional, Union
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
FusionPluginID = Literal["fusion",]
|
||||
|
||||
|
||||
PresetEnum = Union[
|
||||
Literal[
|
||||
"general-high",
|
||||
"general-budget",
|
||||
"general-fast",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""A curated OpenRouter fusion preset (slugs follow `<task>-<tier>`, e.g. `general-high`). Expands server-side into the preset's analysis_models panel and judge model, so callers never name individual models. Explicitly provided `analysis_models` / `model` take precedence."""
|
||||
|
||||
|
||||
class FusionPluginToolTypedDict(TypedDict):
|
||||
type: str
|
||||
r"""Server tool type identifier (e.g. \"openrouter:web_search\", \"openrouter:web_fetch\")."""
|
||||
@@ -34,6 +47,8 @@ class FusionPluginTypedDict(TypedDict):
|
||||
r"""Maximum number of tool-calling steps each panelist (analysis model) and the judge model may take during their agentic web-research loop. Models with web_search/web_fetch enabled iterate until they produce a text response or hit this ceiling. Defaults to 8. Capped at 16."""
|
||||
model: NotRequired[str]
|
||||
r"""Slug of the model that performs both the judge step (with web_search + web_fetch) and the final synthesis. When omitted, defaults to the first model in the Quality preset."""
|
||||
preset: NotRequired[PresetEnum]
|
||||
r"""A curated OpenRouter fusion preset (slugs follow `<task>-<tier>`, e.g. `general-high`). Expands server-side into the preset's analysis_models panel and judge model, so callers never name individual models. Explicitly provided `analysis_models` / `model` take precedence."""
|
||||
tools: NotRequired[List[FusionPluginToolTypedDict]]
|
||||
r"""Server tools available to panelist and judge inner calls. Each entry uses the same `{ type, parameters? }` shorthand as the outer Chat Completions request. When omitted, defaults to `[{ type: \"openrouter:web_search\" }, { type: \"openrouter:web_fetch\" }]`. Pass an empty array to disable tools entirely (panelists answer from parametric knowledge only)."""
|
||||
|
||||
@@ -53,5 +68,10 @@ class FusionPlugin(BaseModel):
|
||||
model: Optional[str] = None
|
||||
r"""Slug of the model that performs both the judge step (with web_search + web_fetch) and the final synthesis. When omitted, defaults to the first model in the Quality preset."""
|
||||
|
||||
preset: Annotated[
|
||||
Optional[PresetEnum], PlainValidator(validate_open_enum(False))
|
||||
] = None
|
||||
r"""A curated OpenRouter fusion preset (slugs follow `<task>-<tier>`, e.g. `general-high`). Expands server-side into the preset's analysis_models panel and judge model, so callers never name individual models. Explicitly provided `analysis_models` / `model` take precedence."""
|
||||
|
||||
tools: Optional[List[FusionPluginTool]] = None
|
||||
r"""Server tools available to panelist and judge inner calls. Each entry uses the same `{ type, parameters? }` shorthand as the outer Chat Completions request. When omitted, defaults to `[{ type: \"openrouter:web_search\" }, { type: \"openrouter:web_fetch\" }]`. Pass an empty array to disable tools entirely (panelists answer from parametric knowledge only)."""
|
||||
|
||||
@@ -1,6 +1,10 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .anthropiccachecontroldirective import (
|
||||
AnthropicCacheControlDirective,
|
||||
AnthropicCacheControlDirectiveTypedDict,
|
||||
)
|
||||
from openrouter.types import BaseModel, Nullable, UnrecognizedStr
|
||||
from openrouter.utils import validate_open_enum
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
@@ -10,6 +14,7 @@ from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
FusionServerToolConfigEffort = Union[
|
||||
Literal[
|
||||
"max",
|
||||
"xhigh",
|
||||
"high",
|
||||
"medium",
|
||||
@@ -64,6 +69,8 @@ class FusionServerToolConfigTypedDict(TypedDict):
|
||||
|
||||
analysis_models: NotRequired[List[str]]
|
||||
r"""Slugs of models to run in parallel as the analysis panel. Each model receives the user prompt with openrouter:web_search and openrouter:web_fetch enabled, then a judge model summarizes the collective output into structured analysis JSON. Capped at 8 models to bound cost amplification. Defaults to the Quality preset from /labs/fusion."""
|
||||
cache_control: NotRequired[AnthropicCacheControlDirectiveTypedDict]
|
||||
r"""Enable automatic prompt caching. When set at the top level, the system automatically applies cache breakpoints to the last cacheable block in the request. Currently supported for Anthropic Claude models."""
|
||||
max_completion_tokens: NotRequired[int]
|
||||
r"""Maximum number of output tokens (including reasoning tokens) each panelist and the judge model may produce per inner call. Controls the total output budget so reasoning-heavy models like GPT-5.5 do not exhaust their token allowance before producing visible text. When omitted, the provider's default applies."""
|
||||
max_tool_calls: NotRequired[int]
|
||||
@@ -73,7 +80,7 @@ class FusionServerToolConfigTypedDict(TypedDict):
|
||||
reasoning: NotRequired[FusionServerToolConfigReasoningTypedDict]
|
||||
r"""Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort and token budget for models that support extended thinking."""
|
||||
temperature: NotRequired[float]
|
||||
r"""Sampling temperature forwarded to panelist and judge inner calls. When omitted, the provider's default applies."""
|
||||
r"""Temperature forwarded to panelist inner calls. The judge always runs at temperature 0 regardless of this value. When omitted, the provider's default applies."""
|
||||
tools: NotRequired[List[FusionServerToolConfigToolTypedDict]]
|
||||
r"""Server tools available to panelist and judge inner calls. Each entry uses the same `{ type, parameters? }` shorthand as the outer Chat Completions request. When omitted, defaults to `[{ type: \"openrouter:web_search\" }, { type: \"openrouter:web_fetch\" }]`. Pass an empty array to disable tools entirely (panelists answer from parametric knowledge only)."""
|
||||
|
||||
@@ -84,6 +91,9 @@ class FusionServerToolConfig(BaseModel):
|
||||
analysis_models: Optional[List[str]] = None
|
||||
r"""Slugs of models to run in parallel as the analysis panel. Each model receives the user prompt with openrouter:web_search and openrouter:web_fetch enabled, then a judge model summarizes the collective output into structured analysis JSON. Capped at 8 models to bound cost amplification. Defaults to the Quality preset from /labs/fusion."""
|
||||
|
||||
cache_control: Optional[AnthropicCacheControlDirective] = None
|
||||
r"""Enable automatic prompt caching. When set at the top level, the system automatically applies cache breakpoints to the last cacheable block in the request. Currently supported for Anthropic Claude models."""
|
||||
|
||||
max_completion_tokens: Optional[int] = None
|
||||
r"""Maximum number of output tokens (including reasoning tokens) each panelist and the judge model may produce per inner call. Controls the total output budget so reasoning-heavy models like GPT-5.5 do not exhaust their token allowance before producing visible text. When omitted, the provider's default applies."""
|
||||
|
||||
@@ -97,7 +107,7 @@ class FusionServerToolConfig(BaseModel):
|
||||
r"""Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort and token budget for models that support extended thinking."""
|
||||
|
||||
temperature: Optional[float] = None
|
||||
r"""Sampling temperature forwarded to panelist and judge inner calls. When omitted, the provider's default applies."""
|
||||
r"""Temperature forwarded to panelist inner calls. The judge always runs at temperature 0 regardless of this value. When omitted, the provider's default applies."""
|
||||
|
||||
tools: Optional[List[FusionServerToolConfigTool]] = None
|
||||
r"""Server tools available to panelist and judge inner calls. Each entry uses the same `{ type, parameters? }` shorthand as the outer Chat Completions request. When omitted, defaults to `[{ type: \"openrouter:web_search\" }, { type: \"openrouter:web_fetch\" }]`. Pass an empty array to disable tools entirely (panelists answer from parametric knowledge only)."""
|
||||
|
||||
@@ -0,0 +1,81 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .capabilitydescriptor import CapabilityDescriptor, CapabilityDescriptorTypedDict
|
||||
from .imagepricingentry import ImagePricingEntry, ImagePricingEntryTypedDict
|
||||
from openrouter.types import BaseModel, Nullable, UNSET_SENTINEL
|
||||
from pydantic import model_serializer
|
||||
from typing import Dict, List
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class ImageEndpointTypedDict(TypedDict):
|
||||
r"""An endpoint that serves a given image model."""
|
||||
|
||||
allowed_passthrough_parameters: List[str]
|
||||
r"""Provider-specific options accepted under provider.options[provider_slug]."""
|
||||
pricing: List[ImagePricingEntryTypedDict]
|
||||
r"""Billable pricing lines for this endpoint."""
|
||||
provider_name: str
|
||||
r"""Provider display name"""
|
||||
provider_slug: str
|
||||
r"""Provider slug"""
|
||||
provider_tag: Nullable[str]
|
||||
r"""Provider tag for request-side selection"""
|
||||
supported_parameters: Dict[str, CapabilityDescriptorTypedDict]
|
||||
supports_streaming: bool
|
||||
r"""Whether this endpoint supports native SSE streaming (`stream: true` in the request)."""
|
||||
|
||||
|
||||
class ImageEndpoint(BaseModel):
|
||||
r"""An endpoint that serves a given image model."""
|
||||
|
||||
allowed_passthrough_parameters: List[str]
|
||||
r"""Provider-specific options accepted under provider.options[provider_slug]."""
|
||||
|
||||
pricing: List[ImagePricingEntry]
|
||||
r"""Billable pricing lines for this endpoint."""
|
||||
|
||||
provider_name: str
|
||||
r"""Provider display name"""
|
||||
|
||||
provider_slug: str
|
||||
r"""Provider slug"""
|
||||
|
||||
provider_tag: Nullable[str]
|
||||
r"""Provider tag for request-side selection"""
|
||||
|
||||
supported_parameters: Dict[str, CapabilityDescriptor]
|
||||
|
||||
supports_streaming: bool
|
||||
r"""Whether this endpoint supports native SSE streaming (`stream: true` in the request)."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = []
|
||||
nullable_fields = ["provider_tag"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,45 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .imagegenerationusage import ImageGenerationUsage, ImageGenerationUsageTypedDict
|
||||
from openrouter.types import BaseModel
|
||||
from typing import Literal, Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
ImageGenCompletedEventType = Literal["image_generation.completed",]
|
||||
r"""The event type"""
|
||||
|
||||
|
||||
class ImageGenCompletedEventTypedDict(TypedDict):
|
||||
r"""Emitted when generation completes and the final image is available"""
|
||||
|
||||
b64_json: str
|
||||
r"""Base64-encoded final image data"""
|
||||
created: int
|
||||
r"""Unix timestamp (seconds) when the image was generated"""
|
||||
type: ImageGenCompletedEventType
|
||||
r"""The event type"""
|
||||
media_type: NotRequired[str]
|
||||
r"""Media type (MIME type) of the image. Omitted when the output is a standard raster format (PNG). Present for non-raster outputs such as SVG (`image/svg+xml`)."""
|
||||
usage: NotRequired[ImageGenerationUsageTypedDict]
|
||||
r"""Token and cost usage for the image generation request, when available"""
|
||||
|
||||
|
||||
class ImageGenCompletedEvent(BaseModel):
|
||||
r"""Emitted when generation completes and the final image is available"""
|
||||
|
||||
b64_json: str
|
||||
r"""Base64-encoded final image data"""
|
||||
|
||||
created: int
|
||||
r"""Unix timestamp (seconds) when the image was generated"""
|
||||
|
||||
type: ImageGenCompletedEventType
|
||||
r"""The event type"""
|
||||
|
||||
media_type: Optional[str] = None
|
||||
r"""Media type (MIME type) of the image. Omitted when the output is a standard raster format (PNG). Present for non-raster outputs such as SVG (`image/svg+xml`)."""
|
||||
|
||||
usage: Optional[ImageGenerationUsage] = None
|
||||
r"""Token and cost usage for the image generation request, when available"""
|
||||
@@ -0,0 +1,610 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .contentpartimage import ContentPartImage, ContentPartImageTypedDict
|
||||
from openrouter.types import BaseModel, Nullable, UnrecognizedStr
|
||||
from openrouter.utils import validate_open_enum
|
||||
import pydantic
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import Any, Dict, List, Literal, Optional, Union
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
ImageGenerationRequestAspectRatio = Union[
|
||||
Literal[
|
||||
"1:1",
|
||||
"1:2",
|
||||
"1:4",
|
||||
"1:8",
|
||||
"2:1",
|
||||
"2:3",
|
||||
"3:2",
|
||||
"3:4",
|
||||
"4:1",
|
||||
"4:3",
|
||||
"4:5",
|
||||
"5:4",
|
||||
"8:1",
|
||||
"9:16",
|
||||
"16:9",
|
||||
"9:19.5",
|
||||
"19.5:9",
|
||||
"9:20",
|
||||
"20:9",
|
||||
"9:21",
|
||||
"21:9",
|
||||
"auto",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""Normalized aspect ratio of the generated image. Providers clamp to their supported subset."""
|
||||
|
||||
|
||||
ImageGenerationRequestBackground = Union[
|
||||
Literal[
|
||||
"auto",
|
||||
"transparent",
|
||||
"opaque",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""Background treatment. `transparent` requires an output_format that supports alpha (png or webp)."""
|
||||
|
||||
|
||||
ImageGenerationRequestOutputFormat = Union[
|
||||
Literal[
|
||||
"png",
|
||||
"jpeg",
|
||||
"webp",
|
||||
"svg",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""Encoding of the returned image bytes. Most models produce raster formats (png, jpeg, webp). SVG is supported by vectorization models (e.g. Quiver) — the SVG markup is UTF-8 base64-encoded in `b64_json`."""
|
||||
|
||||
|
||||
class ImageGenerationRequestOptionsTypedDict(TypedDict):
|
||||
r"""Provider-specific options keyed by provider slug. Only options for the matched provider are forwarded; the rest are ignored. Unrecognized keys are silently dropped."""
|
||||
|
||||
oneai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
ai21: NotRequired[Dict[str, Nullable[Any]]]
|
||||
aion_labs: NotRequired[Dict[str, Nullable[Any]]]
|
||||
akashml: NotRequired[Dict[str, Nullable[Any]]]
|
||||
alibaba: NotRequired[Dict[str, Nullable[Any]]]
|
||||
amazon_bedrock: NotRequired[Dict[str, Nullable[Any]]]
|
||||
amazon_nova: NotRequired[Dict[str, Nullable[Any]]]
|
||||
ambient: NotRequired[Dict[str, Nullable[Any]]]
|
||||
anthropic: NotRequired[Dict[str, Nullable[Any]]]
|
||||
anyscale: NotRequired[Dict[str, Nullable[Any]]]
|
||||
arcee_ai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
atlas_cloud: NotRequired[Dict[str, Nullable[Any]]]
|
||||
atoma: NotRequired[Dict[str, Nullable[Any]]]
|
||||
avian: NotRequired[Dict[str, Nullable[Any]]]
|
||||
azure: NotRequired[Dict[str, Nullable[Any]]]
|
||||
baidu: NotRequired[Dict[str, Nullable[Any]]]
|
||||
baseten: NotRequired[Dict[str, Nullable[Any]]]
|
||||
black_forest_labs: NotRequired[Dict[str, Nullable[Any]]]
|
||||
byteplus: NotRequired[Dict[str, Nullable[Any]]]
|
||||
centml: NotRequired[Dict[str, Nullable[Any]]]
|
||||
cerebras: NotRequired[Dict[str, Nullable[Any]]]
|
||||
chutes: NotRequired[Dict[str, Nullable[Any]]]
|
||||
cirrascale: NotRequired[Dict[str, Nullable[Any]]]
|
||||
clarifai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
cloudflare: NotRequired[Dict[str, Nullable[Any]]]
|
||||
cohere: NotRequired[Dict[str, Nullable[Any]]]
|
||||
crofai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
crucible: NotRequired[Dict[str, Nullable[Any]]]
|
||||
crusoe: NotRequired[Dict[str, Nullable[Any]]]
|
||||
darkbloom: NotRequired[Dict[str, Nullable[Any]]]
|
||||
decart: NotRequired[Dict[str, Nullable[Any]]]
|
||||
deepinfra: NotRequired[Dict[str, Nullable[Any]]]
|
||||
deepseek: NotRequired[Dict[str, Nullable[Any]]]
|
||||
dekallm: NotRequired[Dict[str, Nullable[Any]]]
|
||||
digitalocean: NotRequired[Dict[str, Nullable[Any]]]
|
||||
enfer: NotRequired[Dict[str, Nullable[Any]]]
|
||||
fake_provider: NotRequired[Dict[str, Nullable[Any]]]
|
||||
featherless: NotRequired[Dict[str, Nullable[Any]]]
|
||||
fireworks: NotRequired[Dict[str, Nullable[Any]]]
|
||||
friendli: NotRequired[Dict[str, Nullable[Any]]]
|
||||
gmicloud: NotRequired[Dict[str, Nullable[Any]]]
|
||||
google_ai_studio: NotRequired[Dict[str, Nullable[Any]]]
|
||||
google_vertex: NotRequired[Dict[str, Nullable[Any]]]
|
||||
gopomelo: NotRequired[Dict[str, Nullable[Any]]]
|
||||
groq: NotRequired[Dict[str, Nullable[Any]]]
|
||||
heygen: NotRequired[Dict[str, Nullable[Any]]]
|
||||
huggingface: NotRequired[Dict[str, Nullable[Any]]]
|
||||
hyperbolic: NotRequired[Dict[str, Nullable[Any]]]
|
||||
hyperbolic_quantized: NotRequired[Dict[str, Nullable[Any]]]
|
||||
inception: NotRequired[Dict[str, Nullable[Any]]]
|
||||
inceptron: NotRequired[Dict[str, Nullable[Any]]]
|
||||
inferact_vllm: NotRequired[Dict[str, Nullable[Any]]]
|
||||
inference_net: NotRequired[Dict[str, Nullable[Any]]]
|
||||
infermatic: NotRequired[Dict[str, Nullable[Any]]]
|
||||
inflection: NotRequired[Dict[str, Nullable[Any]]]
|
||||
inocloud: NotRequired[Dict[str, Nullable[Any]]]
|
||||
io_net: NotRequired[Dict[str, Nullable[Any]]]
|
||||
ionstream: NotRequired[Dict[str, Nullable[Any]]]
|
||||
klusterai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
lambda_: NotRequired[Dict[str, Nullable[Any]]]
|
||||
lepton: NotRequired[Dict[str, Nullable[Any]]]
|
||||
liquid: NotRequired[Dict[str, Nullable[Any]]]
|
||||
lynn: NotRequired[Dict[str, Nullable[Any]]]
|
||||
lynn_private: NotRequired[Dict[str, Nullable[Any]]]
|
||||
mancer: NotRequired[Dict[str, Nullable[Any]]]
|
||||
mancer_old: NotRequired[Dict[str, Nullable[Any]]]
|
||||
mara: NotRequired[Dict[str, Nullable[Any]]]
|
||||
meta: NotRequired[Dict[str, Nullable[Any]]]
|
||||
minimax: NotRequired[Dict[str, Nullable[Any]]]
|
||||
mistral: NotRequired[Dict[str, Nullable[Any]]]
|
||||
modal: NotRequired[Dict[str, Nullable[Any]]]
|
||||
modelrun: NotRequired[Dict[str, Nullable[Any]]]
|
||||
modular: NotRequired[Dict[str, Nullable[Any]]]
|
||||
moonshotai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
morph: NotRequired[Dict[str, Nullable[Any]]]
|
||||
ncompass: NotRequired[Dict[str, Nullable[Any]]]
|
||||
nebius: NotRequired[Dict[str, Nullable[Any]]]
|
||||
nex_agi: NotRequired[Dict[str, Nullable[Any]]]
|
||||
nextbit: NotRequired[Dict[str, Nullable[Any]]]
|
||||
nineteen: NotRequired[Dict[str, Nullable[Any]]]
|
||||
novita: NotRequired[Dict[str, Nullable[Any]]]
|
||||
nvidia: NotRequired[Dict[str, Nullable[Any]]]
|
||||
octoai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
open_inference: NotRequired[Dict[str, Nullable[Any]]]
|
||||
openai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
parasail: NotRequired[Dict[str, Nullable[Any]]]
|
||||
perceptron: NotRequired[Dict[str, Nullable[Any]]]
|
||||
perplexity: NotRequired[Dict[str, Nullable[Any]]]
|
||||
phala: NotRequired[Dict[str, Nullable[Any]]]
|
||||
poolside: NotRequired[Dict[str, Nullable[Any]]]
|
||||
quiver: NotRequired[Dict[str, Nullable[Any]]]
|
||||
recraft: NotRequired[Dict[str, Nullable[Any]]]
|
||||
recursal: NotRequired[Dict[str, Nullable[Any]]]
|
||||
reflection: NotRequired[Dict[str, Nullable[Any]]]
|
||||
reka: NotRequired[Dict[str, Nullable[Any]]]
|
||||
relace: NotRequired[Dict[str, Nullable[Any]]]
|
||||
replicate: NotRequired[Dict[str, Nullable[Any]]]
|
||||
sakana_ai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
sambanova: NotRequired[Dict[str, Nullable[Any]]]
|
||||
sambanova_cloaked: NotRequired[Dict[str, Nullable[Any]]]
|
||||
seed: NotRequired[Dict[str, Nullable[Any]]]
|
||||
sf_compute: NotRequired[Dict[str, Nullable[Any]]]
|
||||
siliconflow: NotRequired[Dict[str, Nullable[Any]]]
|
||||
sourceful: NotRequired[Dict[str, Nullable[Any]]]
|
||||
stealth: NotRequired[Dict[str, Nullable[Any]]]
|
||||
stepfun: NotRequired[Dict[str, Nullable[Any]]]
|
||||
streamlake: NotRequired[Dict[str, Nullable[Any]]]
|
||||
switchpoint: NotRequired[Dict[str, Nullable[Any]]]
|
||||
targon: NotRequired[Dict[str, Nullable[Any]]]
|
||||
tenstorrent: NotRequired[Dict[str, Nullable[Any]]]
|
||||
together: NotRequired[Dict[str, Nullable[Any]]]
|
||||
together_lite: NotRequired[Dict[str, Nullable[Any]]]
|
||||
ubicloud: NotRequired[Dict[str, Nullable[Any]]]
|
||||
upstage: NotRequired[Dict[str, Nullable[Any]]]
|
||||
venice: NotRequired[Dict[str, Nullable[Any]]]
|
||||
wafer: NotRequired[Dict[str, Nullable[Any]]]
|
||||
wandb: NotRequired[Dict[str, Nullable[Any]]]
|
||||
xai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
xiaomi: NotRequired[Dict[str, Nullable[Any]]]
|
||||
z_ai: NotRequired[Dict[str, Nullable[Any]]]
|
||||
|
||||
|
||||
class ImageGenerationRequestOptions(BaseModel):
|
||||
r"""Provider-specific options keyed by provider slug. Only options for the matched provider are forwarded; the rest are ignored. Unrecognized keys are silently dropped."""
|
||||
|
||||
oneai: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="01ai")
|
||||
] = None
|
||||
|
||||
ai21: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
aion_labs: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="aion-labs")
|
||||
] = None
|
||||
|
||||
akashml: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
alibaba: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
amazon_bedrock: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="amazon-bedrock")
|
||||
] = None
|
||||
|
||||
amazon_nova: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="amazon-nova")
|
||||
] = None
|
||||
|
||||
ambient: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
anthropic: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
anyscale: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
arcee_ai: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="arcee-ai")
|
||||
] = None
|
||||
|
||||
atlas_cloud: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="atlas-cloud")
|
||||
] = None
|
||||
|
||||
atoma: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
avian: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
azure: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
baidu: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
baseten: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
black_forest_labs: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="black-forest-labs")
|
||||
] = None
|
||||
|
||||
byteplus: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
centml: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
cerebras: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
chutes: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
cirrascale: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
clarifai: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
cloudflare: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
cohere: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
crofai: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
crucible: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
crusoe: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
darkbloom: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
decart: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
deepinfra: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
deepseek: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
dekallm: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
digitalocean: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
enfer: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
fake_provider: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="fake-provider")
|
||||
] = None
|
||||
|
||||
featherless: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
fireworks: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
friendli: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
gmicloud: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
google_ai_studio: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="google-ai-studio")
|
||||
] = None
|
||||
|
||||
google_vertex: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="google-vertex")
|
||||
] = None
|
||||
|
||||
gopomelo: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
groq: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
heygen: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
huggingface: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
hyperbolic: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
hyperbolic_quantized: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="hyperbolic-quantized")
|
||||
] = None
|
||||
|
||||
inception: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
inceptron: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
inferact_vllm: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="inferact-vllm")
|
||||
] = None
|
||||
|
||||
inference_net: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="inference-net")
|
||||
] = None
|
||||
|
||||
infermatic: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
inflection: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
inocloud: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
io_net: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="io-net")
|
||||
] = None
|
||||
|
||||
ionstream: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
klusterai: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
lambda_: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="lambda")
|
||||
] = None
|
||||
|
||||
lepton: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
liquid: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
lynn: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
lynn_private: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="lynn-private")
|
||||
] = None
|
||||
|
||||
mancer: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
mancer_old: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="mancer-old")
|
||||
] = None
|
||||
|
||||
mara: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
meta: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
minimax: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
mistral: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
modal: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
modelrun: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
modular: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
moonshotai: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
morph: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
ncompass: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
nebius: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
nex_agi: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="nex-agi")
|
||||
] = None
|
||||
|
||||
nextbit: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
nineteen: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
novita: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
nvidia: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
octoai: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
open_inference: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="open-inference")
|
||||
] = None
|
||||
|
||||
openai: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
parasail: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
perceptron: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
perplexity: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
phala: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
poolside: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
quiver: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
recraft: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
recursal: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
reflection: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
reka: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
relace: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
replicate: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
sakana_ai: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="sakana-ai")
|
||||
] = None
|
||||
|
||||
sambanova: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
sambanova_cloaked: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="sambanova-cloaked")
|
||||
] = None
|
||||
|
||||
seed: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
sf_compute: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="sf-compute")
|
||||
] = None
|
||||
|
||||
siliconflow: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
sourceful: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
stealth: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
stepfun: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
streamlake: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
switchpoint: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
targon: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
tenstorrent: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
together: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
together_lite: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="together-lite")
|
||||
] = None
|
||||
|
||||
ubicloud: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
upstage: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
venice: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
wafer: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
wandb: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
xai: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
xiaomi: Optional[Dict[str, Nullable[Any]]] = None
|
||||
|
||||
z_ai: Annotated[
|
||||
Optional[Dict[str, Nullable[Any]]], pydantic.Field(alias="z-ai")
|
||||
] = None
|
||||
|
||||
|
||||
class ImageGenerationRequestProviderTypedDict(TypedDict):
|
||||
r"""Provider-specific passthrough configuration"""
|
||||
|
||||
options: NotRequired[ImageGenerationRequestOptionsTypedDict]
|
||||
|
||||
|
||||
class ImageGenerationRequestProvider(BaseModel):
|
||||
r"""Provider-specific passthrough configuration"""
|
||||
|
||||
options: Optional[ImageGenerationRequestOptions] = None
|
||||
|
||||
|
||||
ImageGenerationRequestQuality = Union[
|
||||
Literal[
|
||||
"auto",
|
||||
"low",
|
||||
"medium",
|
||||
"high",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""Rendering quality. Providers without a quality knob ignore this."""
|
||||
|
||||
|
||||
ImageGenerationRequestResolution = Union[
|
||||
Literal[
|
||||
"512",
|
||||
"1K",
|
||||
"2K",
|
||||
"4K",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""Normalized resolution tier of the generated image. Concrete pixel dimensions are derived per-provider."""
|
||||
|
||||
|
||||
class ImageGenerationRequestTypedDict(TypedDict):
|
||||
r"""Image generation request input"""
|
||||
|
||||
model: str
|
||||
r"""The image generation model to use"""
|
||||
prompt: str
|
||||
r"""Text description of the desired image"""
|
||||
aspect_ratio: NotRequired[ImageGenerationRequestAspectRatio]
|
||||
r"""Normalized aspect ratio of the generated image. Providers clamp to their supported subset."""
|
||||
background: NotRequired[ImageGenerationRequestBackground]
|
||||
r"""Background treatment. `transparent` requires an output_format that supports alpha (png or webp)."""
|
||||
input_references: NotRequired[List[ContentPartImageTypedDict]]
|
||||
r"""Reference images to guide image-to-image generation, as base64 data URLs or HTTP(S) URLs."""
|
||||
n: NotRequired[int]
|
||||
r"""Number of images to generate (1-10). Providers that only support single-image generation reject n > 1."""
|
||||
output_compression: NotRequired[int]
|
||||
r"""Compression level (0-100) for webp/jpeg output. Ignored for png and by providers without a compression knob."""
|
||||
output_format: NotRequired[ImageGenerationRequestOutputFormat]
|
||||
r"""Encoding of the returned image bytes. Most models produce raster formats (png, jpeg, webp). SVG is supported by vectorization models (e.g. Quiver) — the SVG markup is UTF-8 base64-encoded in `b64_json`."""
|
||||
provider: NotRequired[ImageGenerationRequestProviderTypedDict]
|
||||
r"""Provider-specific passthrough configuration"""
|
||||
quality: NotRequired[ImageGenerationRequestQuality]
|
||||
r"""Rendering quality. Providers without a quality knob ignore this."""
|
||||
resolution: NotRequired[ImageGenerationRequestResolution]
|
||||
r"""Normalized resolution tier of the generated image. Concrete pixel dimensions are derived per-provider."""
|
||||
seed: NotRequired[int]
|
||||
r"""If specified, the generation will sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed for all providers."""
|
||||
size: NotRequired[str]
|
||||
r"""Optional. A convenience shorthand for output dimensions — pass a tier (\"2K\", \"4K\") or explicit pixels (\"2048x2048\") and we normalize it to the right dimensions for the chosen provider. Interchangeable with resolution + aspect_ratio; use those directly for enumerated, per-model discoverable values. Conflicting size + resolution/aspect_ratio is rejected."""
|
||||
stream: NotRequired[bool]
|
||||
r"""If true, partial images are streamed as SSE events as they become available. Only supported by providers with native streaming (currently OpenAI). Non-streaming providers ignore this flag and return a buffered response."""
|
||||
|
||||
|
||||
class ImageGenerationRequest(BaseModel):
|
||||
r"""Image generation request input"""
|
||||
|
||||
model: str
|
||||
r"""The image generation model to use"""
|
||||
|
||||
prompt: str
|
||||
r"""Text description of the desired image"""
|
||||
|
||||
aspect_ratio: Annotated[
|
||||
Optional[ImageGenerationRequestAspectRatio],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = None
|
||||
r"""Normalized aspect ratio of the generated image. Providers clamp to their supported subset."""
|
||||
|
||||
background: Annotated[
|
||||
Optional[ImageGenerationRequestBackground],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = None
|
||||
r"""Background treatment. `transparent` requires an output_format that supports alpha (png or webp)."""
|
||||
|
||||
input_references: Optional[List[ContentPartImage]] = None
|
||||
r"""Reference images to guide image-to-image generation, as base64 data URLs or HTTP(S) URLs."""
|
||||
|
||||
n: Optional[int] = None
|
||||
r"""Number of images to generate (1-10). Providers that only support single-image generation reject n > 1."""
|
||||
|
||||
output_compression: Optional[int] = None
|
||||
r"""Compression level (0-100) for webp/jpeg output. Ignored for png and by providers without a compression knob."""
|
||||
|
||||
output_format: Annotated[
|
||||
Optional[ImageGenerationRequestOutputFormat],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = None
|
||||
r"""Encoding of the returned image bytes. Most models produce raster formats (png, jpeg, webp). SVG is supported by vectorization models (e.g. Quiver) — the SVG markup is UTF-8 base64-encoded in `b64_json`."""
|
||||
|
||||
provider: Optional[ImageGenerationRequestProvider] = None
|
||||
r"""Provider-specific passthrough configuration"""
|
||||
|
||||
quality: Annotated[
|
||||
Optional[ImageGenerationRequestQuality],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = None
|
||||
r"""Rendering quality. Providers without a quality knob ignore this."""
|
||||
|
||||
resolution: Annotated[
|
||||
Optional[ImageGenerationRequestResolution],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = None
|
||||
r"""Normalized resolution tier of the generated image. Concrete pixel dimensions are derived per-provider."""
|
||||
|
||||
seed: Optional[int] = None
|
||||
r"""If specified, the generation will sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed for all providers."""
|
||||
|
||||
size: Optional[str] = None
|
||||
r"""Optional. A convenience shorthand for output dimensions — pass a tier (\"2K\", \"4K\") or explicit pixels (\"2048x2048\") and we normalize it to the right dimensions for the chosen provider. Interchangeable with resolution + aspect_ratio; use those directly for enumerated, per-model discoverable values. Conflicting size + resolution/aspect_ratio is rejected."""
|
||||
|
||||
stream: Optional[bool] = None
|
||||
r"""If true, partial images are streamed as SSE events as they become available. Only supported by providers with native streaming (currently OpenAI). Non-streaming providers ignore this flag and return a buffered response."""
|
||||
@@ -0,0 +1,46 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .imagegenerationusage import ImageGenerationUsage, ImageGenerationUsageTypedDict
|
||||
from openrouter.types import BaseModel
|
||||
from typing import List, Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
class ImageGenerationResponseDataTypedDict(TypedDict):
|
||||
b64_json: str
|
||||
r"""Base64-encoded image bytes"""
|
||||
media_type: NotRequired[str]
|
||||
r"""Media type (MIME type) of the image. Omitted when the output is a standard raster format (PNG). Present for non-raster outputs such as SVG (`image/svg+xml`)."""
|
||||
|
||||
|
||||
class ImageGenerationResponseData(BaseModel):
|
||||
b64_json: str
|
||||
r"""Base64-encoded image bytes"""
|
||||
|
||||
media_type: Optional[str] = None
|
||||
r"""Media type (MIME type) of the image. Omitted when the output is a standard raster format (PNG). Present for non-raster outputs such as SVG (`image/svg+xml`)."""
|
||||
|
||||
|
||||
class ImageGenerationResponseTypedDict(TypedDict):
|
||||
r"""Image generation response"""
|
||||
|
||||
created: int
|
||||
r"""Unix timestamp (seconds) when the image was generated"""
|
||||
data: List[ImageGenerationResponseDataTypedDict]
|
||||
r"""Generated images"""
|
||||
usage: NotRequired[ImageGenerationUsageTypedDict]
|
||||
r"""Token and cost usage for the image generation request, when available"""
|
||||
|
||||
|
||||
class ImageGenerationResponse(BaseModel):
|
||||
r"""Image generation response"""
|
||||
|
||||
created: int
|
||||
r"""Unix timestamp (seconds) when the image was generated"""
|
||||
|
||||
data: List[ImageGenerationResponseData]
|
||||
r"""Generated images"""
|
||||
|
||||
usage: Optional[ImageGenerationUsage] = None
|
||||
r"""Token and cost usage for the image generation request, when available"""
|
||||
@@ -16,7 +16,7 @@ from typing import Literal, Optional, Union
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
Background = Union[
|
||||
ImageGenerationServerToolBackground = Union[
|
||||
Literal[
|
||||
"transparent",
|
||||
"opaque",
|
||||
@@ -64,7 +64,7 @@ Moderation = Union[
|
||||
]
|
||||
|
||||
|
||||
OutputFormat = Union[
|
||||
ImageGenerationServerToolOutputFormat = Union[
|
||||
Literal[
|
||||
"png",
|
||||
"webp",
|
||||
@@ -74,7 +74,7 @@ OutputFormat = Union[
|
||||
]
|
||||
|
||||
|
||||
Quality = Union[
|
||||
ImageGenerationServerToolQuality = Union[
|
||||
Literal[
|
||||
"low",
|
||||
"medium",
|
||||
@@ -103,15 +103,15 @@ class ImageGenerationServerToolTypedDict(TypedDict):
|
||||
r"""Image generation tool configuration"""
|
||||
|
||||
type: ImageGenerationServerToolType
|
||||
background: NotRequired[Background]
|
||||
background: NotRequired[ImageGenerationServerToolBackground]
|
||||
input_fidelity: NotRequired[Nullable[InputFidelity]]
|
||||
input_image_mask: NotRequired[InputImageMaskTypedDict]
|
||||
model: NotRequired[ModelEnum]
|
||||
moderation: NotRequired[Moderation]
|
||||
output_compression: NotRequired[int]
|
||||
output_format: NotRequired[OutputFormat]
|
||||
output_format: NotRequired[ImageGenerationServerToolOutputFormat]
|
||||
partial_images: NotRequired[int]
|
||||
quality: NotRequired[Quality]
|
||||
quality: NotRequired[ImageGenerationServerToolQuality]
|
||||
size: NotRequired[Size]
|
||||
|
||||
|
||||
@@ -121,7 +121,8 @@ class ImageGenerationServerTool(BaseModel):
|
||||
type: ImageGenerationServerToolType
|
||||
|
||||
background: Annotated[
|
||||
Optional[Background], PlainValidator(validate_open_enum(False))
|
||||
Optional[ImageGenerationServerToolBackground],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = None
|
||||
|
||||
input_fidelity: Annotated[
|
||||
@@ -141,14 +142,16 @@ class ImageGenerationServerTool(BaseModel):
|
||||
output_compression: Optional[int] = None
|
||||
|
||||
output_format: Annotated[
|
||||
Optional[OutputFormat], PlainValidator(validate_open_enum(False))
|
||||
Optional[ImageGenerationServerToolOutputFormat],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = None
|
||||
|
||||
partial_images: Optional[int] = None
|
||||
|
||||
quality: Annotated[Optional[Quality], PlainValidator(validate_open_enum(False))] = (
|
||||
None
|
||||
)
|
||||
quality: Annotated[
|
||||
Optional[ImageGenerationServerToolQuality],
|
||||
PlainValidator(validate_open_enum(False)),
|
||||
] = None
|
||||
|
||||
size: Annotated[Optional[Size], PlainValidator(validate_open_enum(False))] = None
|
||||
|
||||
|
||||
@@ -0,0 +1,331 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .anthropicspeed import AnthropicSpeed
|
||||
from .anthropicusageiteration import (
|
||||
AnthropicUsageIteration,
|
||||
AnthropicUsageIterationTypedDict,
|
||||
)
|
||||
from .costdetails import CostDetails, CostDetailsTypedDict
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
)
|
||||
from openrouter.utils import validate_open_enum
|
||||
from pydantic import model_serializer
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import List, Optional
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
class ImageGenerationUsageCompletionTokensDetailsTypedDict(TypedDict):
|
||||
audio_tokens: NotRequired[Nullable[int]]
|
||||
r"""Tokens generated by the model for audio output."""
|
||||
image_tokens: NotRequired[Nullable[int]]
|
||||
r"""Tokens generated by the model for image output."""
|
||||
reasoning_tokens: NotRequired[Nullable[int]]
|
||||
r"""Tokens generated by the model for reasoning."""
|
||||
|
||||
|
||||
class ImageGenerationUsageCompletionTokensDetails(BaseModel):
|
||||
audio_tokens: OptionalNullable[int] = UNSET
|
||||
r"""Tokens generated by the model for audio output."""
|
||||
|
||||
image_tokens: OptionalNullable[int] = UNSET
|
||||
r"""Tokens generated by the model for image output."""
|
||||
|
||||
reasoning_tokens: OptionalNullable[int] = UNSET
|
||||
r"""Tokens generated by the model for reasoning."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = ["audio_tokens", "image_tokens", "reasoning_tokens"]
|
||||
nullable_fields = ["audio_tokens", "image_tokens", "reasoning_tokens"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
|
||||
|
||||
class ImageGenerationUsagePromptTokensDetailsTypedDict(TypedDict):
|
||||
r"""Breakdown of tokens used in the prompt."""
|
||||
|
||||
audio_tokens: NotRequired[Nullable[int]]
|
||||
r"""Tokens used for input audio."""
|
||||
cache_write_tokens: NotRequired[Nullable[int]]
|
||||
r"""Tokens written to cache. Only returned for models with explicit caching and cache write pricing."""
|
||||
cached_tokens: NotRequired[Nullable[int]]
|
||||
r"""Tokens cached by the endpoint."""
|
||||
file_tokens: NotRequired[Nullable[int]]
|
||||
r"""Tokens used for input files/documents."""
|
||||
video_tokens: NotRequired[Nullable[int]]
|
||||
r"""Tokens used for input video."""
|
||||
|
||||
|
||||
class ImageGenerationUsagePromptTokensDetails(BaseModel):
|
||||
r"""Breakdown of tokens used in the prompt."""
|
||||
|
||||
audio_tokens: OptionalNullable[int] = UNSET
|
||||
r"""Tokens used for input audio."""
|
||||
|
||||
cache_write_tokens: OptionalNullable[int] = UNSET
|
||||
r"""Tokens written to cache. Only returned for models with explicit caching and cache write pricing."""
|
||||
|
||||
cached_tokens: OptionalNullable[int] = UNSET
|
||||
r"""Tokens cached by the endpoint."""
|
||||
|
||||
file_tokens: OptionalNullable[int] = UNSET
|
||||
r"""Tokens used for input files/documents."""
|
||||
|
||||
video_tokens: OptionalNullable[int] = UNSET
|
||||
r"""Tokens used for input video."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"audio_tokens",
|
||||
"cache_write_tokens",
|
||||
"cached_tokens",
|
||||
"file_tokens",
|
||||
"video_tokens",
|
||||
]
|
||||
nullable_fields = [
|
||||
"audio_tokens",
|
||||
"cache_write_tokens",
|
||||
"cached_tokens",
|
||||
"file_tokens",
|
||||
"video_tokens",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
|
||||
|
||||
class ServerToolUseTypedDict(TypedDict):
|
||||
r"""Usage for server-side tool execution (e.g., web search)"""
|
||||
|
||||
tool_calls_executed: NotRequired[Nullable[int]]
|
||||
r"""Number of OpenRouter server tool calls that executed and produced a result."""
|
||||
tool_calls_requested: NotRequired[Nullable[int]]
|
||||
r"""Total number of OpenRouter server-orchestrated tool calls the model requested, across all tool types. Provider-native tools (e.g. native web search) are not counted here."""
|
||||
web_search_requests: NotRequired[Nullable[int]]
|
||||
r"""Number of web searches performed by server-side tools. For server-orchestrated tool calls a web search is also counted in tool_calls_requested; provider-native web search may report web_search_requests only. Do not sum the two."""
|
||||
|
||||
|
||||
class ServerToolUse(BaseModel):
|
||||
r"""Usage for server-side tool execution (e.g., web search)"""
|
||||
|
||||
tool_calls_executed: OptionalNullable[int] = UNSET
|
||||
r"""Number of OpenRouter server tool calls that executed and produced a result."""
|
||||
|
||||
tool_calls_requested: OptionalNullable[int] = UNSET
|
||||
r"""Total number of OpenRouter server-orchestrated tool calls the model requested, across all tool types. Provider-native tools (e.g. native web search) are not counted here."""
|
||||
|
||||
web_search_requests: OptionalNullable[int] = UNSET
|
||||
r"""Number of web searches performed by server-side tools. For server-orchestrated tool calls a web search is also counted in tool_calls_requested; provider-native web search may report web_search_requests only. Do not sum the two."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"tool_calls_executed",
|
||||
"tool_calls_requested",
|
||||
"web_search_requests",
|
||||
]
|
||||
nullable_fields = [
|
||||
"tool_calls_executed",
|
||||
"tool_calls_requested",
|
||||
"web_search_requests",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
|
||||
|
||||
class ImageGenerationUsageTypedDict(TypedDict):
|
||||
r"""Token and cost usage for the image generation request, when available"""
|
||||
|
||||
completion_tokens: int
|
||||
r"""The tokens generated"""
|
||||
prompt_tokens: int
|
||||
r"""Including images, input audio, and tools if any"""
|
||||
total_tokens: int
|
||||
r"""Sum of the above two fields"""
|
||||
completion_tokens_details: NotRequired[
|
||||
Nullable[ImageGenerationUsageCompletionTokensDetailsTypedDict]
|
||||
]
|
||||
cost: NotRequired[Nullable[float]]
|
||||
r"""Cost of the completion"""
|
||||
cost_details: NotRequired[Nullable[CostDetailsTypedDict]]
|
||||
r"""Breakdown of upstream inference costs"""
|
||||
is_byok: NotRequired[bool]
|
||||
r"""Whether a request was made using a Bring Your Own Key configuration"""
|
||||
iterations: NotRequired[Nullable[List[AnthropicUsageIterationTypedDict]]]
|
||||
prompt_tokens_details: NotRequired[
|
||||
Nullable[ImageGenerationUsagePromptTokensDetailsTypedDict]
|
||||
]
|
||||
r"""Breakdown of tokens used in the prompt."""
|
||||
server_tool_use: NotRequired[Nullable[ServerToolUseTypedDict]]
|
||||
r"""Usage for server-side tool execution (e.g., web search)"""
|
||||
service_tier: NotRequired[Nullable[str]]
|
||||
r"""The service tier used by the upstream provider for this request"""
|
||||
speed: NotRequired[Nullable[AnthropicSpeed]]
|
||||
|
||||
|
||||
class ImageGenerationUsage(BaseModel):
|
||||
r"""Token and cost usage for the image generation request, when available"""
|
||||
|
||||
completion_tokens: int
|
||||
r"""The tokens generated"""
|
||||
|
||||
prompt_tokens: int
|
||||
r"""Including images, input audio, and tools if any"""
|
||||
|
||||
total_tokens: int
|
||||
r"""Sum of the above two fields"""
|
||||
|
||||
completion_tokens_details: OptionalNullable[
|
||||
ImageGenerationUsageCompletionTokensDetails
|
||||
] = UNSET
|
||||
|
||||
cost: OptionalNullable[float] = UNSET
|
||||
r"""Cost of the completion"""
|
||||
|
||||
cost_details: OptionalNullable[CostDetails] = UNSET
|
||||
r"""Breakdown of upstream inference costs"""
|
||||
|
||||
is_byok: Optional[bool] = None
|
||||
r"""Whether a request was made using a Bring Your Own Key configuration"""
|
||||
|
||||
iterations: OptionalNullable[List[AnthropicUsageIteration]] = UNSET
|
||||
|
||||
prompt_tokens_details: OptionalNullable[ImageGenerationUsagePromptTokensDetails] = (
|
||||
UNSET
|
||||
)
|
||||
r"""Breakdown of tokens used in the prompt."""
|
||||
|
||||
server_tool_use: OptionalNullable[ServerToolUse] = UNSET
|
||||
r"""Usage for server-side tool execution (e.g., web search)"""
|
||||
|
||||
service_tier: OptionalNullable[str] = UNSET
|
||||
r"""The service tier used by the upstream provider for this request"""
|
||||
|
||||
speed: Annotated[
|
||||
OptionalNullable[AnthropicSpeed], PlainValidator(validate_open_enum(False))
|
||||
] = UNSET
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"completion_tokens_details",
|
||||
"cost",
|
||||
"cost_details",
|
||||
"is_byok",
|
||||
"iterations",
|
||||
"prompt_tokens_details",
|
||||
"server_tool_use",
|
||||
"service_tier",
|
||||
"speed",
|
||||
]
|
||||
nullable_fields = [
|
||||
"completion_tokens_details",
|
||||
"cost",
|
||||
"cost_details",
|
||||
"iterations",
|
||||
"prompt_tokens_details",
|
||||
"server_tool_use",
|
||||
"service_tier",
|
||||
"speed",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,34 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel
|
||||
from typing import Literal
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
ImageGenPartialImageEventType = Literal["image_generation.partial_image",]
|
||||
r"""The event type"""
|
||||
|
||||
|
||||
class ImageGenPartialImageEventTypedDict(TypedDict):
|
||||
r"""Emitted when a partial image becomes available during streaming generation"""
|
||||
|
||||
b64_json: str
|
||||
r"""Base64-encoded partial image data"""
|
||||
partial_image_index: int
|
||||
r"""0-based index indicating which partial image this is in the sequence"""
|
||||
type: ImageGenPartialImageEventType
|
||||
r"""The event type"""
|
||||
|
||||
|
||||
class ImageGenPartialImageEvent(BaseModel):
|
||||
r"""Emitted when a partial image becomes available during streaming generation"""
|
||||
|
||||
b64_json: str
|
||||
r"""Base64-encoded partial image data"""
|
||||
|
||||
partial_image_index: int
|
||||
r"""0-based index indicating which partial image this is in the sequence"""
|
||||
|
||||
type: ImageGenPartialImageEventType
|
||||
r"""The event type"""
|
||||
@@ -0,0 +1,95 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
)
|
||||
from pydantic import model_serializer
|
||||
from typing import Literal
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
class ImageGenStreamErrorEventErrorTypedDict(TypedDict):
|
||||
r"""Provider error details"""
|
||||
|
||||
message: str
|
||||
r"""Provider error message"""
|
||||
code: NotRequired[Nullable[str]]
|
||||
r"""Provider error code, when supplied"""
|
||||
param: NotRequired[Nullable[str]]
|
||||
r"""Request parameter associated with the error, when supplied"""
|
||||
type: NotRequired[Nullable[str]]
|
||||
r"""Provider error type, when supplied"""
|
||||
|
||||
|
||||
class ImageGenStreamErrorEventError(BaseModel):
|
||||
r"""Provider error details"""
|
||||
|
||||
message: str
|
||||
r"""Provider error message"""
|
||||
|
||||
code: OptionalNullable[str] = UNSET
|
||||
r"""Provider error code, when supplied"""
|
||||
|
||||
param: OptionalNullable[str] = UNSET
|
||||
r"""Request parameter associated with the error, when supplied"""
|
||||
|
||||
type: OptionalNullable[str] = UNSET
|
||||
r"""Provider error type, when supplied"""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = ["code", "param", "type"]
|
||||
nullable_fields = ["code", "param", "type"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
|
||||
|
||||
ImageGenStreamErrorEventType = Literal["error",]
|
||||
r"""The event type"""
|
||||
|
||||
|
||||
class ImageGenStreamErrorEventTypedDict(TypedDict):
|
||||
r"""Emitted when streaming generation fails after the SSE response starts"""
|
||||
|
||||
error: ImageGenStreamErrorEventErrorTypedDict
|
||||
r"""Provider error details"""
|
||||
type: ImageGenStreamErrorEventType
|
||||
r"""The event type"""
|
||||
|
||||
|
||||
class ImageGenStreamErrorEvent(BaseModel):
|
||||
r"""Emitted when streaming generation fails after the SSE response starts"""
|
||||
|
||||
error: ImageGenStreamErrorEventError
|
||||
r"""Provider error details"""
|
||||
|
||||
type: ImageGenStreamErrorEventType
|
||||
r"""The event type"""
|
||||
@@ -0,0 +1,29 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .imageoutputmodality import ImageOutputModality
|
||||
from .inputmodality import InputModality
|
||||
from openrouter.types import BaseModel
|
||||
from openrouter.utils import validate_open_enum
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import List
|
||||
from typing_extensions import Annotated, TypedDict
|
||||
|
||||
|
||||
class ImageModelArchitectureTypedDict(TypedDict):
|
||||
input_modalities: List[InputModality]
|
||||
r"""Supported input modalities"""
|
||||
output_modalities: List[ImageOutputModality]
|
||||
r"""Supported output modalities"""
|
||||
|
||||
|
||||
class ImageModelArchitecture(BaseModel):
|
||||
input_modalities: List[
|
||||
Annotated[InputModality, PlainValidator(validate_open_enum(False))]
|
||||
]
|
||||
r"""Supported input modalities"""
|
||||
|
||||
output_modalities: List[
|
||||
Annotated[ImageOutputModality, PlainValidator(validate_open_enum(False))]
|
||||
]
|
||||
r"""Supported output modalities"""
|
||||
@@ -0,0 +1,24 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .imageendpoint import ImageEndpoint, ImageEndpointTypedDict
|
||||
from openrouter.types import BaseModel
|
||||
from typing import List
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class ImageModelEndpointsResponseTypedDict(TypedDict):
|
||||
r"""The full per-endpoint records for an image model."""
|
||||
|
||||
endpoints: List[ImageEndpointTypedDict]
|
||||
id: str
|
||||
r"""Model slug"""
|
||||
|
||||
|
||||
class ImageModelEndpointsResponse(BaseModel):
|
||||
r"""The full per-endpoint records for an image model."""
|
||||
|
||||
endpoints: List[ImageEndpoint]
|
||||
|
||||
id: str
|
||||
r"""Model slug"""
|
||||
@@ -0,0 +1,56 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .capabilitydescriptor import CapabilityDescriptor, CapabilityDescriptorTypedDict
|
||||
from .imagemodelarchitecture import (
|
||||
ImageModelArchitecture,
|
||||
ImageModelArchitectureTypedDict,
|
||||
)
|
||||
from openrouter.types import BaseModel
|
||||
from typing import Dict
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class ImageModelListItemTypedDict(TypedDict):
|
||||
r"""A single image model in the discovery listing."""
|
||||
|
||||
architecture: ImageModelArchitectureTypedDict
|
||||
created: int
|
||||
r"""Unix timestamp (seconds) of when the model was created"""
|
||||
description: str
|
||||
endpoints: str
|
||||
r"""Relative URL to the full per-endpoint records for this model"""
|
||||
id: str
|
||||
r"""Model slug"""
|
||||
name: str
|
||||
r"""Display name"""
|
||||
supported_parameters: Dict[str, CapabilityDescriptorTypedDict]
|
||||
r"""Union of supported parameters across every endpoint of this model. Coarse discovery aid; the definitive per-endpoint set is behind the endpoints URL."""
|
||||
supports_streaming: bool
|
||||
r"""Whether any endpoint of this model supports native SSE streaming on the dedicated Image API (i.e. `stream: true` in the request). OR across endpoints."""
|
||||
|
||||
|
||||
class ImageModelListItem(BaseModel):
|
||||
r"""A single image model in the discovery listing."""
|
||||
|
||||
architecture: ImageModelArchitecture
|
||||
|
||||
created: int
|
||||
r"""Unix timestamp (seconds) of when the model was created"""
|
||||
|
||||
description: str
|
||||
|
||||
endpoints: str
|
||||
r"""Relative URL to the full per-endpoint records for this model"""
|
||||
|
||||
id: str
|
||||
r"""Model slug"""
|
||||
|
||||
name: str
|
||||
r"""Display name"""
|
||||
|
||||
supported_parameters: Dict[str, CapabilityDescriptor]
|
||||
r"""Union of supported parameters across every endpoint of this model. Coarse discovery aid; the definitive per-endpoint set is behind the endpoints URL."""
|
||||
|
||||
supports_streaming: bool
|
||||
r"""Whether any endpoint of this model supports native SSE streaming on the dedicated Image API (i.e. `stream: true` in the request). OR across endpoints."""
|
||||
@@ -0,0 +1,19 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .imagemodellistitem import ImageModelListItem, ImageModelListItemTypedDict
|
||||
from openrouter.types import BaseModel
|
||||
from typing import List
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class ImageModelsListResponseTypedDict(TypedDict):
|
||||
r"""List of image generation models."""
|
||||
|
||||
data: List[ImageModelListItemTypedDict]
|
||||
|
||||
|
||||
class ImageModelsListResponse(BaseModel):
|
||||
r"""List of image generation models."""
|
||||
|
||||
data: List[ImageModelListItem]
|
||||
@@ -0,0 +1,20 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import UnrecognizedStr
|
||||
from typing import Literal, Union
|
||||
|
||||
|
||||
ImageOutputModality = Union[
|
||||
Literal[
|
||||
"text",
|
||||
"image",
|
||||
"embeddings",
|
||||
"audio",
|
||||
"video",
|
||||
"rerank",
|
||||
"speech",
|
||||
"transcription",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
@@ -0,0 +1,51 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel, UnrecognizedStr
|
||||
from openrouter.utils import validate_open_enum
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import Literal, Optional, Union
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
Billable = Union[
|
||||
Literal[
|
||||
"output_image",
|
||||
"input_image",
|
||||
"input_font",
|
||||
"input_reference",
|
||||
"input_text",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
|
||||
|
||||
Unit = Union[
|
||||
Literal[
|
||||
"image",
|
||||
"megapixel",
|
||||
"token",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
|
||||
|
||||
class ImagePricingEntryTypedDict(TypedDict):
|
||||
r"""One billable pricing line for an image provider."""
|
||||
|
||||
billable: Billable
|
||||
cost_usd: float
|
||||
unit: Unit
|
||||
variant: NotRequired[str]
|
||||
|
||||
|
||||
class ImagePricingEntry(BaseModel):
|
||||
r"""One billable pricing line for an image provider."""
|
||||
|
||||
billable: Annotated[Billable, PlainValidator(validate_open_enum(False))]
|
||||
|
||||
cost_usd: float
|
||||
|
||||
unit: Annotated[Unit, PlainValidator(validate_open_enum(False))]
|
||||
|
||||
variant: Optional[str] = None
|
||||
@@ -0,0 +1,48 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .imagegencompletedevent import (
|
||||
ImageGenCompletedEvent,
|
||||
ImageGenCompletedEventTypedDict,
|
||||
)
|
||||
from .imagegenpartialimageevent import (
|
||||
ImageGenPartialImageEvent,
|
||||
ImageGenPartialImageEventTypedDict,
|
||||
)
|
||||
from .imagegenstreamerrorevent import (
|
||||
ImageGenStreamErrorEvent,
|
||||
ImageGenStreamErrorEventTypedDict,
|
||||
)
|
||||
from openrouter.types import BaseModel
|
||||
from openrouter.utils import get_discriminator
|
||||
from pydantic import Discriminator, Tag
|
||||
from typing import Union
|
||||
from typing_extensions import Annotated, TypeAliasType, TypedDict
|
||||
|
||||
|
||||
ImageStreamingResponseDataTypedDict = TypeAliasType(
|
||||
"ImageStreamingResponseDataTypedDict",
|
||||
Union[
|
||||
ImageGenStreamErrorEventTypedDict,
|
||||
ImageGenPartialImageEventTypedDict,
|
||||
ImageGenCompletedEventTypedDict,
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
ImageStreamingResponseData = Annotated[
|
||||
Union[
|
||||
Annotated[ImageGenPartialImageEvent, Tag("image_generation.partial_image")],
|
||||
Annotated[ImageGenCompletedEvent, Tag("image_generation.completed")],
|
||||
Annotated[ImageGenStreamErrorEvent, Tag("error")],
|
||||
],
|
||||
Discriminator(lambda m: get_discriminator(m, "type", "type")),
|
||||
]
|
||||
|
||||
|
||||
class ImageStreamingResponseTypedDict(TypedDict):
|
||||
data: ImageStreamingResponseDataTypedDict
|
||||
|
||||
|
||||
class ImageStreamingResponse(BaseModel):
|
||||
data: ImageStreamingResponseData
|
||||
@@ -84,6 +84,10 @@ from .outputfunctioncallitem import (
|
||||
OutputFunctionCallItem,
|
||||
OutputFunctionCallItemTypedDict,
|
||||
)
|
||||
from .outputfusionservertoolitem import (
|
||||
OutputFusionServerToolItem,
|
||||
OutputFusionServerToolItemTypedDict,
|
||||
)
|
||||
from .outputimagegenerationcallitem import (
|
||||
OutputImageGenerationCallItem,
|
||||
OutputImageGenerationCallItemTypedDict,
|
||||
@@ -104,6 +108,10 @@ from .outputsearchmodelsservertoolitem import (
|
||||
OutputSearchModelsServerToolItem,
|
||||
OutputSearchModelsServerToolItemTypedDict,
|
||||
)
|
||||
from .outputsubagentservertoolitem import (
|
||||
OutputSubagentServerToolItem,
|
||||
OutputSubagentServerToolItemTypedDict,
|
||||
)
|
||||
from .outputtexteditorservertoolitem import (
|
||||
OutputTextEditorServerToolItem,
|
||||
OutputTextEditorServerToolItemTypedDict,
|
||||
@@ -388,44 +396,46 @@ InputsUnion1TypedDict = TypeAliasType(
|
||||
OutputFileSearchCallItemTypedDict,
|
||||
EasyInputMessageTypedDict,
|
||||
InputMessageItemTypedDict,
|
||||
CustomToolCallOutputItemTypedDict,
|
||||
LocalShellCallOutputItemTypedDict,
|
||||
OutputToolSearchServerToolItemTypedDict,
|
||||
OutputFileSearchServerToolItemTypedDict,
|
||||
OutputWebSearchServerToolItemTypedDict,
|
||||
CustomToolCallOutputItemTypedDict,
|
||||
OutputImageGenerationCallItemTypedDict,
|
||||
OutputWebSearchCallItemTypedDict,
|
||||
OutputDatetimeItemTypedDict,
|
||||
OutputMcpServerToolItemTypedDict,
|
||||
FunctionCallOutputItemTypedDict,
|
||||
LocalShellCallItemTypedDict,
|
||||
OutputSearchModelsServerToolItemTypedDict,
|
||||
FunctionCallOutputItemTypedDict,
|
||||
ApplyPatchCallItemTypedDict,
|
||||
OutputDatetimeItemTypedDict,
|
||||
McpApprovalResponseItemTypedDict,
|
||||
McpApprovalRequestItemTypedDict,
|
||||
McpListToolsItemTypedDict,
|
||||
ApplyPatchCallOutputItemTypedDict,
|
||||
McpApprovalResponseItemTypedDict,
|
||||
OutputBrowserUseServerToolItemTypedDict,
|
||||
McpApprovalRequestItemTypedDict,
|
||||
OutputMcpServerToolItemTypedDict,
|
||||
OutputTextEditorServerToolItemTypedDict,
|
||||
OutputApplyPatchServerToolItemTypedDict,
|
||||
CustomToolCallItemTypedDict,
|
||||
ShellCallItemTypedDict,
|
||||
InputsMessageTypedDict,
|
||||
OutputMemoryServerToolItemTypedDict,
|
||||
OutputCustomToolCallItemTypedDict,
|
||||
ShellCallItemTypedDict,
|
||||
ShellCallOutputItemTypedDict,
|
||||
OutputComputerCallItemTypedDict,
|
||||
OutputCodeInterpreterCallItemTypedDict,
|
||||
OutputImageGenerationServerToolItemTypedDict,
|
||||
OutputBashServerToolItemTypedDict,
|
||||
OutputCustomToolCallItemTypedDict,
|
||||
OutputComputerCallItemTypedDict,
|
||||
CustomToolCallItemTypedDict,
|
||||
ShellCallOutputItemTypedDict,
|
||||
McpCallItemTypedDict,
|
||||
OutputImageGenerationServerToolItemTypedDict,
|
||||
OutputFunctionCallItemTypedDict,
|
||||
OutputBashServerToolItemTypedDict,
|
||||
FunctionCallItemTypedDict,
|
||||
OutputAdvisorServerToolItemTypedDict,
|
||||
OutputWebFetchServerToolItemTypedDict,
|
||||
ReasoningItemTypedDict,
|
||||
OutputCodeInterpreterServerToolItemTypedDict,
|
||||
OutputSubagentServerToolItemTypedDict,
|
||||
InputsReasoningTypedDict,
|
||||
OutputCodeInterpreterServerToolItemTypedDict,
|
||||
OutputWebFetchServerToolItemTypedDict,
|
||||
OutputAdvisorServerToolItemTypedDict,
|
||||
OutputFusionServerToolItemTypedDict,
|
||||
],
|
||||
)
|
||||
|
||||
@@ -438,44 +448,46 @@ InputsUnion1 = TypeAliasType(
|
||||
OutputFileSearchCallItem,
|
||||
EasyInputMessage,
|
||||
InputMessageItem,
|
||||
CustomToolCallOutputItem,
|
||||
LocalShellCallOutputItem,
|
||||
OutputToolSearchServerToolItem,
|
||||
OutputFileSearchServerToolItem,
|
||||
OutputWebSearchServerToolItem,
|
||||
CustomToolCallOutputItem,
|
||||
OutputImageGenerationCallItem,
|
||||
OutputWebSearchCallItem,
|
||||
OutputDatetimeItem,
|
||||
OutputMcpServerToolItem,
|
||||
FunctionCallOutputItem,
|
||||
LocalShellCallItem,
|
||||
OutputSearchModelsServerToolItem,
|
||||
FunctionCallOutputItem,
|
||||
ApplyPatchCallItem,
|
||||
OutputDatetimeItem,
|
||||
McpApprovalResponseItem,
|
||||
McpApprovalRequestItem,
|
||||
McpListToolsItem,
|
||||
ApplyPatchCallOutputItem,
|
||||
McpApprovalResponseItem,
|
||||
OutputBrowserUseServerToolItem,
|
||||
McpApprovalRequestItem,
|
||||
OutputMcpServerToolItem,
|
||||
OutputTextEditorServerToolItem,
|
||||
OutputApplyPatchServerToolItem,
|
||||
CustomToolCallItem,
|
||||
ShellCallItem,
|
||||
InputsMessage,
|
||||
OutputMemoryServerToolItem,
|
||||
OutputCustomToolCallItem,
|
||||
ShellCallItem,
|
||||
ShellCallOutputItem,
|
||||
OutputComputerCallItem,
|
||||
OutputCodeInterpreterCallItem,
|
||||
OutputImageGenerationServerToolItem,
|
||||
OutputBashServerToolItem,
|
||||
OutputCustomToolCallItem,
|
||||
OutputComputerCallItem,
|
||||
CustomToolCallItem,
|
||||
ShellCallOutputItem,
|
||||
McpCallItem,
|
||||
OutputImageGenerationServerToolItem,
|
||||
OutputFunctionCallItem,
|
||||
OutputBashServerToolItem,
|
||||
FunctionCallItem,
|
||||
OutputAdvisorServerToolItem,
|
||||
OutputWebFetchServerToolItem,
|
||||
ReasoningItem,
|
||||
OutputCodeInterpreterServerToolItem,
|
||||
OutputSubagentServerToolItem,
|
||||
InputsReasoning,
|
||||
OutputCodeInterpreterServerToolItem,
|
||||
OutputWebFetchServerToolItem,
|
||||
OutputAdvisorServerToolItem,
|
||||
OutputFusionServerToolItem,
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
@@ -27,10 +27,10 @@ class LegacyWebSearchServerToolTypedDict(TypedDict):
|
||||
|
||||
type: LegacyWebSearchServerToolType
|
||||
engine: NotRequired[WebSearchEngineEnum]
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API."""
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API. \"perplexity\" uses the Perplexity Search API (raw ranked results)."""
|
||||
filters: NotRequired[Nullable[WebSearchDomainFilterTypedDict]]
|
||||
max_results: NotRequired[int]
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, and Parallel engines; ignored with native provider search."""
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, Parallel, and Perplexity engines; ignored with native provider search. Perplexity supports a maximum of 20; values above 20 are clamped."""
|
||||
search_context_size: NotRequired[SearchContextSizeEnum]
|
||||
r"""Size of the search context for web search tools"""
|
||||
user_location: NotRequired[Nullable[WebSearchUserLocationTypedDict]]
|
||||
@@ -45,12 +45,12 @@ class LegacyWebSearchServerTool(BaseModel):
|
||||
engine: Annotated[
|
||||
Optional[WebSearchEngineEnum], PlainValidator(validate_open_enum(False))
|
||||
] = None
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API."""
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API. \"perplexity\" uses the Perplexity Search API (raw ranked results)."""
|
||||
|
||||
filters: OptionalNullable[WebSearchDomainFilter] = UNSET
|
||||
|
||||
max_results: Optional[int] = None
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, and Parallel engines; ignored with native provider search."""
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, Parallel, and Perplexity engines; ignored with native provider search. Perplexity supports a maximum of 20; values above 20 are clamped."""
|
||||
|
||||
search_context_size: Annotated[
|
||||
Optional[SearchContextSizeEnum], PlainValidator(validate_open_enum(False))
|
||||
|
||||
@@ -0,0 +1,17 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .workspacebudget import WorkspaceBudget, WorkspaceBudgetTypedDict
|
||||
from openrouter.types import BaseModel
|
||||
from typing import List
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class ListWorkspaceBudgetsResponseTypedDict(TypedDict):
|
||||
data: List[WorkspaceBudgetTypedDict]
|
||||
r"""List of budgets configured for the workspace"""
|
||||
|
||||
|
||||
class ListWorkspaceBudgetsResponse(BaseModel):
|
||||
data: List[WorkspaceBudget]
|
||||
r"""List of budgets configured for the workspace"""
|
||||
@@ -0,0 +1,33 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from openrouter.types import BaseModel, Nullable
|
||||
import pydantic
|
||||
from pydantic import ConfigDict
|
||||
from typing import Any, Dict
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class MessagesFallbackParamTypedDict(TypedDict):
|
||||
r"""Fallback model to try when the primary model fails or refuses. Only the `model` field is supported; per-attempt overrides are rejected."""
|
||||
|
||||
model: str
|
||||
|
||||
|
||||
class MessagesFallbackParam(BaseModel):
|
||||
r"""Fallback model to try when the primary model fails or refuses. Only the `model` field is supported; per-attempt overrides are rejected."""
|
||||
|
||||
model_config = ConfigDict(
|
||||
populate_by_name=True, arbitrary_types_allowed=True, extra="allow"
|
||||
)
|
||||
__pydantic_extra__: Dict[str, Nullable[Any]] = pydantic.Field(init=False)
|
||||
|
||||
model: str
|
||||
|
||||
@property
|
||||
def additional_properties(self):
|
||||
return self.__pydantic_extra__
|
||||
|
||||
@additional_properties.setter
|
||||
def additional_properties(self, value):
|
||||
self.__pydantic_extra__ = value # pyright: ignore[reportIncompatibleVariableOverride]
|
||||
@@ -50,6 +50,7 @@ from .imagegenerationservertool_openrouter import (
|
||||
ImageGenerationServerToolOpenRouter,
|
||||
ImageGenerationServerToolOpenRouterTypedDict,
|
||||
)
|
||||
from .messagesfallbackparam import MessagesFallbackParam, MessagesFallbackParamTypedDict
|
||||
from .messagesmessageparam import MessagesMessageParam, MessagesMessageParamTypedDict
|
||||
from .messagesoutputconfig import MessagesOutputConfig, MessagesOutputConfigTypedDict
|
||||
from .moderationplugin import ModerationPlugin, ModerationPluginTypedDict
|
||||
@@ -297,11 +298,11 @@ class ContextManagement(BaseModel):
|
||||
edits: Optional[List[Edit]] = None
|
||||
|
||||
|
||||
class MetadataTypedDict(TypedDict):
|
||||
class MessagesRequestMetadataTypedDict(TypedDict):
|
||||
user_id: NotRequired[Nullable[str]]
|
||||
|
||||
|
||||
class Metadata(BaseModel):
|
||||
class MessagesRequestMetadata(BaseModel):
|
||||
user_id: OptionalNullable[str] = UNSET
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
@@ -1046,8 +1047,10 @@ class MessagesRequestTypedDict(TypedDict):
|
||||
cache_control: NotRequired[AnthropicCacheControlDirectiveTypedDict]
|
||||
r"""Enable automatic prompt caching. When set at the top level, the system automatically applies cache breakpoints to the last cacheable block in the request. Currently supported for Anthropic Claude models."""
|
||||
context_management: NotRequired[Nullable[ContextManagementTypedDict]]
|
||||
fallbacks: NotRequired[Nullable[List[MessagesFallbackParamTypedDict]]]
|
||||
r"""Fallback models to try if the primary model fails or refuses, in order. Handled by OpenRouter multi-model routing rather than Anthropic server-side fallbacks; cannot be combined with `models`. Each entry accepts only `model`. Maximum of 3 entries."""
|
||||
max_tokens: NotRequired[int]
|
||||
metadata: NotRequired[MetadataTypedDict]
|
||||
metadata: NotRequired[MessagesRequestMetadataTypedDict]
|
||||
models: NotRequired[List[str]]
|
||||
output_config: NotRequired[MessagesOutputConfigTypedDict]
|
||||
r"""Configuration for controlling output behavior. Supports the effort parameter and structured output format."""
|
||||
@@ -1088,9 +1091,12 @@ class MessagesRequest(BaseModel):
|
||||
|
||||
context_management: OptionalNullable[ContextManagement] = UNSET
|
||||
|
||||
fallbacks: OptionalNullable[List[MessagesFallbackParam]] = UNSET
|
||||
r"""Fallback models to try if the primary model fails or refuses, in order. Handled by OpenRouter multi-model routing rather than Anthropic server-side fallbacks; cannot be combined with `models`. Each entry accepts only `model`. Maximum of 3 entries."""
|
||||
|
||||
max_tokens: Optional[int] = None
|
||||
|
||||
metadata: Optional[Metadata] = None
|
||||
metadata: Optional[MessagesRequestMetadata] = None
|
||||
|
||||
models: Optional[List[str]] = None
|
||||
|
||||
@@ -1144,6 +1150,7 @@ class MessagesRequest(BaseModel):
|
||||
optional_fields = [
|
||||
"cache_control",
|
||||
"context_management",
|
||||
"fallbacks",
|
||||
"max_tokens",
|
||||
"metadata",
|
||||
"models",
|
||||
@@ -1166,7 +1173,13 @@ class MessagesRequest(BaseModel):
|
||||
"trace",
|
||||
"user",
|
||||
]
|
||||
nullable_fields = ["context_management", "messages", "provider", "speed"]
|
||||
nullable_fields = [
|
||||
"context_management",
|
||||
"fallbacks",
|
||||
"messages",
|
||||
"provider",
|
||||
"speed",
|
||||
]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
@@ -3,7 +3,9 @@
|
||||
from __future__ import annotations
|
||||
from .defaultparameters import DefaultParameters, DefaultParametersTypedDict
|
||||
from .modelarchitecture import ModelArchitecture, ModelArchitectureTypedDict
|
||||
from .modelbenchmarks import ModelBenchmarks, ModelBenchmarksTypedDict
|
||||
from .modellinks import ModelLinks, ModelLinksTypedDict
|
||||
from .modelreasoning import ModelReasoning, ModelReasoningTypedDict
|
||||
from .parameter import Parameter
|
||||
from .perrequestlimits import PerRequestLimits, PerRequestLimitsTypedDict
|
||||
from .publicpricing import PublicPricing, PublicPricingTypedDict
|
||||
@@ -51,6 +53,8 @@ class ModelTypedDict(TypedDict):
|
||||
r"""List of supported voice identifiers for TTS models. Null for non-TTS models."""
|
||||
top_provider: TopProviderInfoTypedDict
|
||||
r"""Information about the top provider for this model"""
|
||||
benchmarks: NotRequired[ModelBenchmarksTypedDict]
|
||||
r"""Third-party benchmark rankings for this model. Omitted when no benchmark data is available."""
|
||||
description: NotRequired[str]
|
||||
r"""Description of the model"""
|
||||
expiration_date: NotRequired[Nullable[str]]
|
||||
@@ -59,6 +63,8 @@ class ModelTypedDict(TypedDict):
|
||||
r"""Hugging Face model identifier, if applicable"""
|
||||
knowledge_cutoff: NotRequired[Nullable[str]]
|
||||
r"""The date up to which the model was trained on data. ISO 8601 date string (YYYY-MM-DD) or null if unknown."""
|
||||
reasoning: NotRequired[ModelReasoningTypedDict]
|
||||
r"""Reasoning effort configuration. Omitted for non-reasoning models and dynamic router models."""
|
||||
|
||||
|
||||
class Model(BaseModel):
|
||||
@@ -105,6 +111,9 @@ class Model(BaseModel):
|
||||
top_provider: TopProviderInfo
|
||||
r"""Information about the top provider for this model"""
|
||||
|
||||
benchmarks: Optional[ModelBenchmarks] = None
|
||||
r"""Third-party benchmark rankings for this model. Omitted when no benchmark data is available."""
|
||||
|
||||
description: Optional[str] = None
|
||||
r"""Description of the model"""
|
||||
|
||||
@@ -117,13 +126,18 @@ class Model(BaseModel):
|
||||
knowledge_cutoff: OptionalNullable[str] = UNSET
|
||||
r"""The date up to which the model was trained on data. ISO 8601 date string (YYYY-MM-DD) or null if unknown."""
|
||||
|
||||
reasoning: Optional[ModelReasoning] = None
|
||||
r"""Reasoning effort configuration. Omitted for non-reasoning models and dynamic router models."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"benchmarks",
|
||||
"description",
|
||||
"expiration_date",
|
||||
"hugging_face_id",
|
||||
"knowledge_cutoff",
|
||||
"reasoning",
|
||||
]
|
||||
nullable_fields = [
|
||||
"context_length",
|
||||
|
||||
@@ -0,0 +1,27 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .aabenchmarkentry import AABenchmarkEntry, AABenchmarkEntryTypedDict
|
||||
from .dabenchmarkentry import DABenchmarkEntry, DABenchmarkEntryTypedDict
|
||||
from openrouter.types import BaseModel
|
||||
from typing import List, Optional
|
||||
from typing_extensions import NotRequired, TypedDict
|
||||
|
||||
|
||||
class ModelBenchmarksTypedDict(TypedDict):
|
||||
r"""Third-party benchmark rankings for this model. Omitted when no benchmark data is available."""
|
||||
|
||||
design_arena: List[DABenchmarkEntryTypedDict]
|
||||
r"""Design Arena ELO rankings across arena+category pairs."""
|
||||
artificial_analysis: NotRequired[AABenchmarkEntryTypedDict]
|
||||
r"""Artificial Analysis benchmark index scores."""
|
||||
|
||||
|
||||
class ModelBenchmarks(BaseModel):
|
||||
r"""Third-party benchmark rankings for this model. Omitted when no benchmark data is available."""
|
||||
|
||||
design_arena: List[DABenchmarkEntry]
|
||||
r"""Design Arena ELO rankings across arena+category pairs."""
|
||||
|
||||
artificial_analysis: Optional[AABenchmarkEntry] = None
|
||||
r"""Artificial Analysis benchmark index scores."""
|
||||
@@ -0,0 +1,107 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .reasoningeffort import ReasoningEffort
|
||||
from openrouter.types import (
|
||||
BaseModel,
|
||||
Nullable,
|
||||
OptionalNullable,
|
||||
UNSET,
|
||||
UNSET_SENTINEL,
|
||||
UnrecognizedStr,
|
||||
)
|
||||
from openrouter.utils import validate_open_enum
|
||||
from pydantic import model_serializer
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import List, Literal, Optional, Union
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
DefaultEffort = Union[
|
||||
Literal[
|
||||
"max",
|
||||
"xhigh",
|
||||
"high",
|
||||
"medium",
|
||||
"low",
|
||||
"minimal",
|
||||
"none",
|
||||
],
|
||||
UnrecognizedStr,
|
||||
]
|
||||
r"""Default reasoning effort when the client enables reasoning without specifying effort. Maps to `reasoning.effort` in chat requests. When `\"none\"`, prefer omitting effort unless the user explicitly disables reasoning."""
|
||||
|
||||
|
||||
class ModelReasoningTypedDict(TypedDict):
|
||||
r"""Reasoning effort configuration. Omitted for non-reasoning models and dynamic router models."""
|
||||
|
||||
mandatory: bool
|
||||
r"""When true, reasoning cannot be disabled and effort \"none\" is rejected."""
|
||||
default_effort: NotRequired[Nullable[DefaultEffort]]
|
||||
default_enabled: NotRequired[bool]
|
||||
r"""Default reasoning enabled state when the client does not set `reasoning.enabled`."""
|
||||
supported_efforts: NotRequired[Nullable[List[Nullable[ReasoningEffort]]]]
|
||||
r"""Allowed reasoning effort values for this model, in descending effort order (highest first). Null means no allowlist — all gateway effort values are accepted."""
|
||||
supports_max_tokens: NotRequired[bool]
|
||||
r"""Present and `true` when the model accepts `reasoning.max_tokens` in requests (Anthropic-style) instead of or in addition to `reasoning.effort`. Omitted otherwise."""
|
||||
|
||||
|
||||
class ModelReasoning(BaseModel):
|
||||
r"""Reasoning effort configuration. Omitted for non-reasoning models and dynamic router models."""
|
||||
|
||||
mandatory: bool
|
||||
r"""When true, reasoning cannot be disabled and effort \"none\" is rejected."""
|
||||
|
||||
default_effort: Annotated[
|
||||
OptionalNullable[DefaultEffort], PlainValidator(validate_open_enum(False))
|
||||
] = UNSET
|
||||
|
||||
default_enabled: Optional[bool] = None
|
||||
r"""Default reasoning enabled state when the client does not set `reasoning.enabled`."""
|
||||
|
||||
supported_efforts: OptionalNullable[
|
||||
List[
|
||||
Annotated[
|
||||
Nullable[ReasoningEffort], PlainValidator(validate_open_enum(False))
|
||||
]
|
||||
]
|
||||
] = UNSET
|
||||
r"""Allowed reasoning effort values for this model, in descending effort order (highest first). Null means no allowlist — all gateway effort values are accepted."""
|
||||
|
||||
supports_max_tokens: Optional[bool] = None
|
||||
r"""Present and `true` when the model accepts `reasoning.max_tokens` in requests (Anthropic-style) instead of or in addition to `reasoning.effort`. Omitted otherwise."""
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
def serialize_model(self, handler):
|
||||
optional_fields = [
|
||||
"default_effort",
|
||||
"default_enabled",
|
||||
"supported_efforts",
|
||||
"supports_max_tokens",
|
||||
]
|
||||
nullable_fields = ["default_effort", "supported_efforts"]
|
||||
null_default_fields = []
|
||||
|
||||
serialized = handler(self)
|
||||
|
||||
m = {}
|
||||
|
||||
for n, f in type(self).model_fields.items():
|
||||
k = f.alias or n
|
||||
val = serialized.get(k)
|
||||
serialized.pop(k, None)
|
||||
|
||||
optional_nullable = k in optional_fields and k in nullable_fields
|
||||
is_set = (
|
||||
self.__pydantic_fields_set__.intersection({n})
|
||||
or k in null_default_fields
|
||||
) # pylint: disable=no-member
|
||||
|
||||
if val is not None and val != UNSET_SENTINEL:
|
||||
m[k] = val
|
||||
elif val != UNSET_SENTINEL and (
|
||||
not k in optional_fields or (optional_nullable and is_set)
|
||||
):
|
||||
m[k] = val
|
||||
|
||||
return m
|
||||
@@ -0,0 +1,20 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .model import Model, ModelTypedDict
|
||||
from openrouter.types import BaseModel
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class ModelResponseTypedDict(TypedDict):
|
||||
r"""Single model response"""
|
||||
|
||||
data: ModelTypedDict
|
||||
r"""Information about an AI model available on OpenRouter"""
|
||||
|
||||
|
||||
class ModelResponse(BaseModel):
|
||||
r"""Single model response"""
|
||||
|
||||
data: Model
|
||||
r"""Information about an AI model available on OpenRouter"""
|
||||
@@ -15,6 +15,7 @@ from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
class ObservabilityArizeDestinationConfigTypedDict(TypedDict):
|
||||
api_key: str
|
||||
model_id: str
|
||||
r"""The name of the tracing project in Arize AX"""
|
||||
space_key: str
|
||||
base_url: NotRequired[str]
|
||||
headers: NotRequired[Dict[str, str]]
|
||||
@@ -25,6 +26,7 @@ class ObservabilityArizeDestinationConfig(BaseModel):
|
||||
api_key: Annotated[str, pydantic.Field(alias="apiKey")]
|
||||
|
||||
model_id: Annotated[str, pydantic.Field(alias="modelId")]
|
||||
r"""The name of the tracing project in Arize AX"""
|
||||
|
||||
space_key: Annotated[str, pydantic.Field(alias="spaceKey")]
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .apierrortype import APIErrorType
|
||||
from .applypatchservertool import ApplyPatchServerTool, ApplyPatchServerToolTypedDict
|
||||
from .baseinputs_union import BaseInputsUnion, BaseInputsUnionTypedDict
|
||||
from .basereasoningconfig import BaseReasoningConfig, BaseReasoningConfigTypedDict
|
||||
@@ -203,6 +204,8 @@ class OpenResponsesResultTypedDict(TypedDict):
|
||||
usage: NotRequired[Nullable[UsageTypedDict]]
|
||||
r"""Token usage information for the response"""
|
||||
user: NotRequired[Nullable[str]]
|
||||
error_type: NotRequired[APIErrorType]
|
||||
r"""Canonical OpenRouter error type, stable across all API formats"""
|
||||
openrouter_metadata: NotRequired[OpenRouterMetadataTypedDict]
|
||||
|
||||
|
||||
@@ -285,6 +288,11 @@ class OpenResponsesResult(BaseModel):
|
||||
|
||||
user: OptionalNullable[str] = UNSET
|
||||
|
||||
error_type: Annotated[
|
||||
Optional[APIErrorType], PlainValidator(validate_open_enum(False))
|
||||
] = None
|
||||
r"""Canonical OpenRouter error type, stable across all API formats"""
|
||||
|
||||
openrouter_metadata: Optional[OpenRouterMetadata] = None
|
||||
|
||||
@model_serializer(mode="wrap")
|
||||
@@ -306,6 +314,7 @@ class OpenResponsesResult(BaseModel):
|
||||
"truncation",
|
||||
"usage",
|
||||
"user",
|
||||
"error_type",
|
||||
"openrouter_metadata",
|
||||
]
|
||||
nullable_fields = [
|
||||
|
||||
@@ -81,6 +81,10 @@ from .outputshellcalloutputitem import (
|
||||
OutputShellCallOutputItem,
|
||||
OutputShellCallOutputItemTypedDict,
|
||||
)
|
||||
from .outputsubagentservertoolitem import (
|
||||
OutputSubagentServerToolItem,
|
||||
OutputSubagentServerToolItemTypedDict,
|
||||
)
|
||||
from .outputtexteditorservertoolitem import (
|
||||
OutputTextEditorServerToolItem,
|
||||
OutputTextEditorServerToolItemTypedDict,
|
||||
@@ -138,6 +142,7 @@ OutputItemsTypedDict = TypeAliasType(
|
||||
OutputReasoningItemTypedDict,
|
||||
OutputFusionServerToolItemTypedDict,
|
||||
OutputAdvisorServerToolItemTypedDict,
|
||||
OutputSubagentServerToolItemTypedDict,
|
||||
],
|
||||
)
|
||||
r"""An output item from the response"""
|
||||
@@ -172,6 +177,7 @@ OutputItems = Annotated[
|
||||
],
|
||||
Annotated[OutputMcpServerToolItem, Tag("openrouter:mcp")],
|
||||
Annotated[OutputMemoryServerToolItem, Tag("openrouter:memory")],
|
||||
Annotated[OutputSubagentServerToolItem, Tag("openrouter:subagent")],
|
||||
Annotated[OutputTextEditorServerToolItem, Tag("openrouter:text_editor")],
|
||||
Annotated[OutputToolSearchServerToolItem, Tag("openrouter:tool_search")],
|
||||
Annotated[OutputWebFetchServerToolItem, Tag("openrouter:web_fetch")],
|
||||
|
||||
@@ -0,0 +1,55 @@
|
||||
"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
|
||||
|
||||
from __future__ import annotations
|
||||
from .toolcallstatus import ToolCallStatus
|
||||
from openrouter.types import BaseModel
|
||||
from openrouter.utils import validate_open_enum
|
||||
from pydantic.functional_validators import PlainValidator
|
||||
from typing import Literal, Optional
|
||||
from typing_extensions import Annotated, NotRequired, TypedDict
|
||||
|
||||
|
||||
OutputSubagentServerToolItemType = Literal["openrouter:subagent",]
|
||||
|
||||
|
||||
class OutputSubagentServerToolItemTypedDict(TypedDict):
|
||||
r"""An openrouter:subagent server tool output item"""
|
||||
|
||||
status: ToolCallStatus
|
||||
type: OutputSubagentServerToolItemType
|
||||
error: NotRequired[str]
|
||||
r"""Error message when the subagent task did not produce an outcome."""
|
||||
id: NotRequired[str]
|
||||
model: NotRequired[str]
|
||||
r"""Slug of the worker model that executed the task."""
|
||||
outcome: NotRequired[str]
|
||||
r"""The worker model's result (the outcome text returned to the delegating model)."""
|
||||
task_description: NotRequired[str]
|
||||
r"""The task description the delegating model sent to the worker."""
|
||||
task_name: NotRequired[str]
|
||||
r"""The short task identifier the delegating model supplied."""
|
||||
|
||||
|
||||
class OutputSubagentServerToolItem(BaseModel):
|
||||
r"""An openrouter:subagent server tool output item"""
|
||||
|
||||
status: Annotated[ToolCallStatus, PlainValidator(validate_open_enum(False))]
|
||||
|
||||
type: OutputSubagentServerToolItemType
|
||||
|
||||
error: Optional[str] = None
|
||||
r"""Error message when the subagent task did not produce an outcome."""
|
||||
|
||||
id: Optional[str] = None
|
||||
|
||||
model: Optional[str] = None
|
||||
r"""Slug of the worker model that executed the task."""
|
||||
|
||||
outcome: Optional[str] = None
|
||||
r"""The worker model's result (the outcome text returned to the delegating model)."""
|
||||
|
||||
task_description: Optional[str] = None
|
||||
r"""The task description the delegating model sent to the worker."""
|
||||
|
||||
task_name: Optional[str] = None
|
||||
r"""The short task identifier the delegating model supplied."""
|
||||
@@ -30,10 +30,10 @@ class Preview20250311WebSearchServerToolTypedDict(TypedDict):
|
||||
|
||||
type: Preview20250311WebSearchServerToolType
|
||||
engine: NotRequired[WebSearchEngineEnum]
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API."""
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API. \"perplexity\" uses the Perplexity Search API (raw ranked results)."""
|
||||
filters: NotRequired[Nullable[WebSearchDomainFilterTypedDict]]
|
||||
max_results: NotRequired[int]
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, and Parallel engines; ignored with native provider search."""
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, Parallel, and Perplexity engines; ignored with native provider search. Perplexity supports a maximum of 20; values above 20 are clamped."""
|
||||
search_context_size: NotRequired[SearchContextSizeEnum]
|
||||
r"""Size of the search context for web search tools"""
|
||||
user_location: NotRequired[Nullable[PreviewWebSearchUserLocationTypedDict]]
|
||||
@@ -47,12 +47,12 @@ class Preview20250311WebSearchServerTool(BaseModel):
|
||||
engine: Annotated[
|
||||
Optional[WebSearchEngineEnum], PlainValidator(validate_open_enum(False))
|
||||
] = None
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API."""
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API. \"perplexity\" uses the Perplexity Search API (raw ranked results)."""
|
||||
|
||||
filters: OptionalNullable[WebSearchDomainFilter] = UNSET
|
||||
|
||||
max_results: Optional[int] = None
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, and Parallel engines; ignored with native provider search."""
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, Parallel, and Perplexity engines; ignored with native provider search. Perplexity supports a maximum of 20; values above 20 are clamped."""
|
||||
|
||||
search_context_size: Annotated[
|
||||
Optional[SearchContextSizeEnum], PlainValidator(validate_open_enum(False))
|
||||
|
||||
@@ -30,10 +30,10 @@ class PreviewWebSearchServerToolTypedDict(TypedDict):
|
||||
|
||||
type: PreviewWebSearchServerToolType
|
||||
engine: NotRequired[WebSearchEngineEnum]
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API."""
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API. \"perplexity\" uses the Perplexity Search API (raw ranked results)."""
|
||||
filters: NotRequired[Nullable[WebSearchDomainFilterTypedDict]]
|
||||
max_results: NotRequired[int]
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, and Parallel engines; ignored with native provider search."""
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, Parallel, and Perplexity engines; ignored with native provider search. Perplexity supports a maximum of 20; values above 20 are clamped."""
|
||||
search_context_size: NotRequired[SearchContextSizeEnum]
|
||||
r"""Size of the search context for web search tools"""
|
||||
user_location: NotRequired[Nullable[PreviewWebSearchUserLocationTypedDict]]
|
||||
@@ -47,12 +47,12 @@ class PreviewWebSearchServerTool(BaseModel):
|
||||
engine: Annotated[
|
||||
Optional[WebSearchEngineEnum], PlainValidator(validate_open_enum(False))
|
||||
] = None
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API."""
|
||||
r"""Which search engine to use. \"auto\" (default) uses native if the provider supports it, otherwise Exa. \"native\" forces the provider's built-in search. \"exa\" forces the Exa search API. \"firecrawl\" uses Firecrawl (requires BYOK). \"parallel\" uses the Parallel search API. \"perplexity\" uses the Perplexity Search API (raw ranked results)."""
|
||||
|
||||
filters: OptionalNullable[WebSearchDomainFilter] = UNSET
|
||||
|
||||
max_results: Optional[int] = None
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, and Parallel engines; ignored with native provider search."""
|
||||
r"""Maximum number of search results to return per search call. Defaults to 5. Applies to Exa, Firecrawl, Parallel, and Perplexity engines; ignored with native provider search. Perplexity supports a maximum of 20; values above 20 are clamped."""
|
||||
|
||||
search_context_size: Annotated[
|
||||
Optional[SearchContextSizeEnum], PlainValidator(validate_open_enum(False))
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user