Compare commits

..
1105 changed files with 10888 additions and 171551 deletions
-11
View File
@@ -1,11 +0,0 @@
{
"permissions": {
"allow": [
"Bash(python3:*)",
"Bash(git push:*)",
"Bash(gh pr create:*)"
],
"deny": [],
"ask": []
}
}
+1 -1
View File
@@ -1,6 +1,6 @@
<div align="center">
<a href="https://codespaces.new/OpenRouterTeam/python-sdk.git/tree/main"><img src="https://github.com/codespaces/badge.svg" /></a>
<a href="https://codespaces.new/speakeasy-sdks/openrouter-python-sdk.git/tree/main"><img src="https://github.com/codespaces/badge.svg" /></a>
</div>
<br>
-1
View File
@@ -1 +0,0 @@
pylintrc
@@ -1,225 +0,0 @@
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"
-46
View File
@@ -1,46 +0,0 @@
name: Notify Monorepo of Changes
on:
push:
branches:
- main
jobs:
notify-monorepo:
runs-on: ubuntu-latest
steps:
- name: Send repository dispatch to monorepo
run: |
# Determine which event type to send based on repository name
REPO_NAME="${GITHUB_REPOSITORY#*/}" # Gets 'python-sdk' from 'OpenRouterTeam/python-sdk'
case "$REPO_NAME" in
"typescript-sdk")
EVENT_TYPE="sync-typescript-sdk"
;;
"python-sdk")
EVENT_TYPE="sync-python-sdk"
;;
"ai-sdk-provider")
EVENT_TYPE="sync-ai-sdk-provider"
;;
"cli")
EVENT_TYPE="sync-cli"
;;
*)
echo "Unknown repository: $REPO_NAME"
exit 1
;;
esac
echo "Sending repository_dispatch event: $EVENT_TYPE"
curl -L \
-X POST \
-H "Accept: application/vnd.github+json" \
-H "Authorization: Bearer ${{ secrets.MONOREPO_SYNC_TOKEN }}" \
-H "X-GitHub-Api-Version: 2022-11-28" \
https://api.github.com/repos/OpenRouterTeam/openrouter-web/dispatches \
-d "{\"event_type\":\"$EVENT_TYPE\",\"client_payload\":{\"repository\":\"$GITHUB_REPOSITORY\",\"ref\":\"$GITHUB_REF\",\"sha\":\"$GITHUB_SHA\"}}"
echo "✅ Notification sent to monorepo"
-37
View File
@@ -1,37 +0,0 @@
name: PR Validation
on:
pull_request:
paths-ignore:
- .speakeasy/in.openapi.yaml
concurrency:
group: pr-validation-${{ 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
-70
View File
@@ -21,11 +21,6 @@ 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
@@ -35,69 +30,4 @@ jobs:
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 }}
@@ -1,104 +0,0 @@
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 }}
@@ -1,23 +1,19 @@
name: Publish
name: Speakeasy Tagging
permissions:
checks: write
contents: write
pull-requests: write
statuses: write
id-token: write
"on":
push:
branches:
- main
paths:
- .speakeasy/gen.lock
workflow_dispatch: {}
jobs:
publish:
uses: speakeasy-api/sdk-generation-action/.github/workflows/sdk-publish.yaml@v15
tag:
uses: speakeasy-api/sdk-generation-action/.github/workflows/tag.yaml@v15
with:
target: open-router
registry_tags: main
secrets:
github_access_token: ${{ secrets.GITHUB_TOKEN }}
pypi_token: ${{ secrets.PYPI_TOKEN }}
speakeasy_api_key: ${{ secrets.SPEAKEASY_API_KEY }}
speakeasy_api_key: ${{ secrets.SPEAKEASY_API_KEY }}
+3 -15
View File
@@ -1,25 +1,13 @@
.env.local
.venv/
venv/
src/*.egg-info/
**/__pycache__/
.pytest_cache/
.python-version
.DS_Store
pyrightconfig.json
**/.speakeasy/temp/
**/.speakeasy/logs/
.speakeasy/reports
# Build artifacts
/dist
__pycache__/
*.py[cod]
*.egg-info/
*.egg
# Speakeasy generation artifacts (generated in OSS repo, not here)
.speakeasy/*.lock
.speakeasy/*.openapi.yaml
/docs
# Environment
.env
.env.local
.env.*.local
.DS_Store
.venv/
+249 -10532
View File
File diff suppressed because it is too large Load Diff
+10 -28
View File
@@ -6,7 +6,7 @@ generation:
sdkClassName: OpenRouter
maintainOpenAPIOrder: true
usageSnippets:
optionalPropertyRendering: never
optionalPropertyRendering: withExample
sdkInitStyle: constructor
useClassNamesForArrayFields: true
fixes:
@@ -22,67 +22,49 @@ generation:
hoistGlobalSecurity: true
inferSSEOverload: true
sdkHooksConfigAccess: true
schemas:
allOfMergeStrategy: shallowMerge
requestBodyFieldName: ""
persistentEdits: {}
tests:
generateTests: false
generateNewTests: true
skipResponseBodyAssertions: false
preApplyUnionDiscriminators: true
python:
version: 0.10.4
version: 0.6.3
additionalDependencies:
dev: {}
main: {}
allowedRedefinedBuiltins:
- id
- object
- input
- models
- hash
asyncMode: both
authors:
- OpenRouter
- Speakeasy
baseErrorName: OpenRouterError
clientServerStatusCodesAsErrors: true
constFieldCasing: upper
defaultErrorName: OpenRouterDefaultError
description: Official Python Client SDK for OpenRouter.
enableCustomCodeRegions: false
description: Python Client SDK Generated by Speakeasy.
enableCustomCodeRegions: true
enumFormat: union
envVarPrefix: OPENROUTER
fixFlags:
asyncPaginationSep2025: true
responseRequiredSep2024: true
flattenGlobalSecurity: true
flattenRequests: true
flatteningOrder: parameters-first
forwardCompatibleUnionsByDefault: tagged-only
imports:
option: openapi
paths:
callbacks: callbacks
callbacks: ""
errors: errors
operations: operations
shared: components
webhooks: webhooks
inferSSEOverload: true
inferUnionDiscriminators: true
operations: ""
shared: ""
webhooks: ""
inputModelSuffix: input
legacyPyright: false
license: Apache-2.0
maxMethodParams: 999
methodArguments: infer-optional-args
moduleName: ""
multipartArrayFormat: legacy
outputModelSuffix: output
packageManager: uv
packageName: openrouter
preApplyUnionDiscriminators: false
pytestFilterWarnings: []
pytestTimeout: 0
responseFormat: flat
sseFlatResponse: true
sseFlatResponse: false
templateVersion: v2
+1345 -33970
View File
File diff suppressed because it is too large Load Diff
-10
View File
@@ -1,10 +0,0 @@
lintVersion: 1.0.0
defaultRuleset: openrouter
rulesets:
openrouter:
rulesets:
- speakeasy-recommended
- speakeasy-generation
rules:
oas3-missing-example:
severity: "off"
File diff suppressed because it is too large Load Diff
+1350 -33919
View File
File diff suppressed because it is too large Load Diff
@@ -1,52 +0,0 @@
overlay: 1.0.0
x-speakeasy-jsonpath: rfc9535
info:
title: Add HTTP-Referer and X-OpenRouter-Title as global parameters
version: 0.0.0
actions:
# Add global parameters for app identification
- target: $
description: Add x-speakeasy-globals for HTTP-Referer, X-OpenRouter-Title, and X-OpenRouter-Categories headers
update:
x-speakeasy-globals:
parameters:
- $ref: "#/components/parameters/AppIdentifier"
- $ref: "#/components/parameters/AppDisplayName"
- $ref: "#/components/parameters/AppCategories"
# Add component parameters
- target: $.components
description: Add parameters for app identification headers
update:
parameters:
AppIdentifier:
name: HTTP-Referer
in: header
schema:
type: string
description: |
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.
AppDisplayName:
name: X-OpenRouter-Title
in: header
schema:
type: string
description: |
The app display name allows you to customize how your app appears in OpenRouter's dashboard.
AppCategories:
name: X-OpenRouter-Categories
in: header
schema:
type: string
description: |
Comma-separated list of app categories (e.g. "cli-agent,cloud-agent"). Used for marketplace rankings.
# Add header parameters to all paths so Speakeasy matches them with globals
- target: $.paths[*]
description: Reference app identification headers on all paths so Speakeasy injects them via globals
update:
parameters:
- $ref: "#/components/parameters/AppIdentifier"
- $ref: "#/components/parameters/AppDisplayName"
- $ref: "#/components/parameters/AppCategories"
@@ -1,11 +0,0 @@
overlay: 1.0.0
x-speakeasy-jsonpath: rfc9535
info:
title: Simplify redundant allOf inline schemas
version: 0.0.0
actions:
- target: "$..allOf[?@.enum && !@['$ref']]"
description: >
Remove inline enum definitions that duplicate a $ref enum in the same
allOf. These are artifacts from zod-openapi .extend() serialization.
remove: true
@@ -1,10 +0,0 @@
overlay: 1.0.0
x-speakeasy-jsonpath: rfc9535
info:
title: Convert boolean query params from string to boolean
version: 0.0.0
actions:
- target: $..parameters[?@.schema["x-openrouter-type"] == "boolean"].schema
description: Convert x-openrouter-type boolean params from string to boolean
update:
type: boolean
@@ -1,10 +0,0 @@
overlay: 1.0.0
x-speakeasy-jsonpath: rfc9535
info:
title: Fix nullable pagination params
version: 0.0.0
actions:
- target: $..parameters[?@.name == "offset" && @.in == "query"].schema
description: Remove nullable from offset query params to fix mypy errors in pagination helpers
update:
nullable: false
@@ -1,10 +0,0 @@
overlay: 1.0.0
x-speakeasy-jsonpath: rfc9535
info:
title: Add open enums
version: 0.0.0
actions:
- target: $..[?length(@.enum) > 1]
description: Automatically open all enums that have length > 1
update:
x-speakeasy-unknown-values: allow
@@ -1,15 +0,0 @@
overlay: 1.0.0
x-speakeasy-jsonpath: rfc9535
info:
title: Remove RSS+XML response schemas and related parameters
version: 0.0.0
actions:
- target: $..responses.*.content["application/rss+xml"]
description: Remove application/rss+xml response schemas
remove: true
- target: $..parameters[?@.name == "use_rss"]
description: Remove use_rss parameter
remove: true
- target: $..parameters[?@.name == "use_rss_chat_links"]
description: Remove use_rss_chat_links parameter
remove: true
+15 -25
View File
@@ -1,48 +1,38 @@
speakeasyVersion: 1.680.0
speakeasyVersion: 1.617.1
sources:
OpenRouter API:
OpenRouter Chat Completions API:
sourceNamespace: open-router-chat-completions-api
sourceRevisionDigest: sha256:04b1417598cd30a7ea0db043f95705d05abee22a86750cb49d1f872ff0aac1a0
sourceBlobDigest: sha256:8af92c8bafad9bb39a0d61b02a3ac2a6002ba1f37a620db676a62529f844cf7c
sourceRevisionDigest: sha256:a7746404e672bbb6dcd8354532d0c627d24522844c39d58011d4cd9c7e8ebd20
sourceBlobDigest: sha256:67c793fef9c039a2c351fc6ba7ed9a6119059023fe3fbd1022645d7494c2c63c
tags:
- latest
- speakeasy-sdk-regen-1782475583
- speakeasy-sdk-regen-1757290070
- 1.0.0
targets:
open-router:
source: OpenRouter API
source: OpenRouter Chat Completions API
sourceNamespace: open-router-chat-completions-api
sourceRevisionDigest: sha256:04b1417598cd30a7ea0db043f95705d05abee22a86750cb49d1f872ff0aac1a0
sourceBlobDigest: sha256:8af92c8bafad9bb39a0d61b02a3ac2a6002ba1f37a620db676a62529f844cf7c
codeSamplesNamespace: open-router-python-code-samples
codeSamplesRevisionDigest: sha256:9eb822c39464f6b8ff4cbbe3e2f0bacc6abed49eea905c340948a45c826f7dc0
sourceRevisionDigest: sha256:a7746404e672bbb6dcd8354532d0c627d24522844c39d58011d4cd9c7e8ebd20
sourceBlobDigest: sha256:67c793fef9c039a2c351fc6ba7ed9a6119059023fe3fbd1022645d7494c2c63c
codeSamplesNamespace: open-router-chat-completions-api-python-code-samples
codeSamplesRevisionDigest: sha256:fb054934c4d0de58a48ca8cdfde7b4210f71c425fb9dfad02e8824b8a1848774
workflow:
workflowVersion: 1.0.0
speakeasyVersion: 1.680.0
speakeasyVersion: latest
sources:
OpenRouter API:
OpenRouter Chat Completions API:
inputs:
- location: .speakeasy/in.openapi.yaml
overlays:
- location: .speakeasy/overlays/open-enums.overlay.yaml
- location: .speakeasy/overlays/remove-rss-responses.overlay.yaml
- location: .speakeasy/overlays/add-headers.overlay.yaml
- location: .speakeasy/overlays/allof-simplify.overlay.yaml
- location: .speakeasy/overlays/boolean-query-params.overlay.yaml
- location: .speakeasy/overlays/fix-nullable-pagination.overlay.yaml
output: .speakeasy/out.openapi.yaml
registry:
location: registry.speakeasyapi.dev/openrouter/sdk/open-router-chat-completions-api
location: registry.speakeasyapi.dev/sheldon-vaughn-test/sandbox/open-router-chat-completions-api
targets:
open-router:
target: python
source: OpenRouter API
publish:
pypi:
token: $pypi_token
source: OpenRouter Chat Completions API
codeSamples:
registry:
location: registry.speakeasyapi.dev/openrouter/sdk/open-router-python-code-samples
location: registry.speakeasyapi.dev/sheldon-vaughn-test/sandbox/open-router-chat-completions-api-python-code-samples
labelOverride:
fixedValue: Python (SDK)
blocking: false
+5 -15
View File
@@ -1,29 +1,19 @@
workflowVersion: 1.0.0
speakeasyVersion: 1.680.0
speakeasyVersion: latest
sources:
OpenRouter API:
OpenRouter Chat Completions API:
inputs:
- location: .speakeasy/in.openapi.yaml
overlays:
- location: .speakeasy/overlays/open-enums.overlay.yaml
- location: .speakeasy/overlays/remove-rss-responses.overlay.yaml
- location: .speakeasy/overlays/add-headers.overlay.yaml
- location: .speakeasy/overlays/allof-simplify.overlay.yaml
- location: .speakeasy/overlays/boolean-query-params.overlay.yaml
- location: .speakeasy/overlays/fix-nullable-pagination.overlay.yaml
output: .speakeasy/out.openapi.yaml
registry:
location: registry.speakeasyapi.dev/openrouter/sdk/open-router-chat-completions-api
location: registry.speakeasyapi.dev/sheldon-vaughn-test/sandbox/open-router-chat-completions-api
targets:
open-router:
target: python
source: OpenRouter API
publish:
pypi:
token: $pypi_token
source: OpenRouter Chat Completions API
codeSamples:
registry:
location: registry.speakeasyapi.dev/openrouter/sdk/open-router-python-code-samples
location: registry.speakeasyapi.dev/sheldon-vaughn-test/sandbox/open-router-chat-completions-api-python-code-samples
labelOverride:
fixedValue: Python (SDK)
blocking: false
-201
View File
@@ -1,201 +0,0 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-127
View File
@@ -1,127 +0,0 @@
# OpenRouter Python SDK
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?
Integrating AI models into applications involves handling different provider APIs, managing model-specific requirements, and avoiding common implementation mistakes. The OpenRouter SDK standardizes these integrations and protects you from footguns.
```python
from openrouter import OpenRouter
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY")
) as client:
response = client.chat.send(
model="minimax/minimax-m2",
messages=[
{"role": "user", "content": "Explain quantum computing"}
]
)
```
The SDK provides three core benefits:
### Auto-generated from API specifications
The SDK is automatically generated from OpenRouter's OpenAPI specs and updated with every API change. New models, parameters, and features appear in your IDE autocomplete immediately. No manual updates. No version drift.
```python
# When new models launch, they're available instantly
response = client.chat.send(
model="minimax/minimax-m2"
)
```
### Type-safe by default
Every parameter, response field, and configuration option is fully typed with Python type hints and validated with Pydantic. Invalid configurations are caught at runtime with clear error messages.
```python
response = client.chat.send(
model="minimax/minimax-m2",
messages=[
{"role": "user", "content": "Hello"}
# ← Pydantic validates message structure
],
temperature=0.7, # ← Type-checked and validated
stream=True # ← Response type changes based on this
)
```
**Actionable error messages:**
```python
# Instead of generic errors, get specific guidance:
# "Model 'openai/o1-preview' requires at least 2 messages.
# You provided 1 message. Add a system or user message."
```
**Type-safe streaming:**
```python
stream = client.chat.send(
model="minimax/minimax-m2",
messages=[{"role": "user", "content": "Write a story"}],
stream=True
)
for event in stream:
# Full type information for streaming responses
content = event.choices[0].delta.content if event.choices else None
```
**Async support:**
```python
import asyncio
async def main():
async with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY")
) as client:
response = await client.chat.send_async(
model="minimax/minimax-m2",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)
asyncio.run(main())
```
## Installation
```bash
# Using uv (recommended)
uv add openrouter
# Using pip
pip install openrouter
# Using poetry
poetry add openrouter
```
**Requirements:** Python 3.9 or higher
Get your API key from [openrouter.ai/settings/keys](https://openrouter.ai/settings/keys).
## Quick start
```python
from openrouter import OpenRouter
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY")
) as client:
response = client.chat.send(
model="minimax/minimax-m2",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)
```
+411 -116
View File
@@ -1,16 +1,50 @@
# 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 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).
<!-- No Summary [summary] -->
<div align="center">
<img width="500" height="300" alt="image" src="https://github.com/user-attachments/assets/19d8ad52-cb56-4f87-8bce-9a9c2233ac16" />
<h1>OpenRouter Python SDK</h1>
<p>Developer-friendly Python SDK specifically catered to leverage the <strong>OpenRouter</strong> API.</p>
<a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge" /></a>
</div>
<!-- No Table of Contents [toc] -->
<!-- Start Summary [summary] -->
## Summary
OpenRouter Chat Completions API: OpenAI-compatible Chat Completions API with additional OpenRouter features
For more information about the API: [OpenRouter Documentation](https://openrouter.ai/docs)
<!-- End Summary [summary] -->
<!-- Start Table of Contents [toc] -->
## Table of Contents
<!-- $toc-max-depth=2 -->
* [SDK Installation](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#sdk-installation)
* [IDE Support](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#ide-support)
* [SDK Example Usage](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#sdk-example-usage)
* [Authentication](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#authentication)
* [Available Resources and Operations](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#available-resources-and-operations)
* [Server-sent event streaming](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#server-sent-event-streaming)
* [Retries](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#retries)
* [Error Handling](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#error-handling)
* [Server Selection](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#server-selection)
* [Custom HTTP Client](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#custom-http-client)
* [Resource Management](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#resource-management)
* [Debugging](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#debugging)
* [Development](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#development)
* [Maturity](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#maturity)
* [Contributions](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#contributions)
<!-- End Table of Contents [toc] -->
<!-- Start SDK Installation [installation] -->
## SDK Installation
> [!TIP]
> To finish publishing your SDK to PyPI you must [run your first generation action](https://www.speakeasy.com/docs/github-setup#step-by-step-guide).
> [!NOTE]
> **Python version upgrade policy**
>
@@ -23,7 +57,7 @@ The SDK can be installed with *uv*, *pip*, or *poetry* package managers.
*uv* is a fast Python package installer and resolver, designed as a drop-in replacement for pip and pip-tools. It's recommended for its speed and modern Python tooling capabilities.
```bash
uv add openrouter
uv add git+https://github.com/speakeasy-sdks/openrouter-python-sdk.git
```
### PIP
@@ -31,7 +65,7 @@ uv add openrouter
*PIP* is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.
```bash
pip install openrouter
pip install git+https://github.com/speakeasy-sdks/openrouter-python-sdk.git
```
### Poetry
@@ -39,7 +73,7 @@ pip install openrouter
*Poetry* is a modern tool that simplifies dependency management and package publishing by using a single `pyproject.toml` file to handle project metadata and dependencies.
```bash
poetry add openrouter
poetry add git+https://github.com/speakeasy-sdks/openrouter-python-sdk.git
```
### Shell and script usage with `uv`
@@ -74,12 +108,6 @@ Once that is saved to a file, you can run it with `uv run script.py` where
`script.py` can be replaced with the actual file name.
<!-- End SDK Installation [installation] -->
<!-- Start Requirements [requirements] -->
## Requirements
This SDK requires Python 3.9 or higher. For Python version support policy, see the SDK Installation section above.
<!-- End Requirements [requirements] -->
<!-- Start IDE Support [idesupport] -->
## IDE Support
@@ -90,8 +118,10 @@ Generally, the SDK will work well with most IDEs out of the box. However, when u
- [PyCharm Pydantic Plugin](https://docs.pydantic.dev/latest/integrations/pycharm/)
<!-- End IDE Support [idesupport] -->
<!-- No SDK Example Usage [usage] -->
## SDK Usage
<!-- Start SDK Example Usage [usage] -->
## SDK Example Usage
### Example
```python
# Synchronous Example
@@ -103,25 +133,22 @@ with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.send(messages=[
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], model="anthropic/claude-4.5-sonnet", provider={
"zdr": True,
"sort": "price",
}, stream=True)
], stream=False, temperature=1, top_p=1)
for event in event_stream:
# handle event
print(event, flush=True)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
</br>
The same SDK client can also be used to make asynchronous requests by importing asyncio.
```python
# Asynchronous Example
import asyncio
@@ -134,80 +161,83 @@ async def main():
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = await open_router.chat.send_async(messages=[
res = await open_router.chat.complete_async(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
async with res as event_stream:
async for event in event_stream:
# handle event
print(event, flush=True)
asyncio.run(main())
```
<!-- End SDK Example Usage [usage] -->
<!-- Start Authentication [security] -->
## Authentication
### Per-Client Security Schemes
This SDK supports the following security scheme globally:
| Name | Type | Scheme | Environment Variable |
| --------- | ---- | ----------- | -------------------- |
| `api_key` | http | HTTP Bearer | `OPENROUTER_API_KEY` |
To authenticate with the API the `api_key` parameter must be set when initializing the SDK client instance. For example:
```python
from openrouter import OpenRouter
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], model="anthropic/claude-4.5-sonnet", provider={
"zdr": True,
"sort": "price",
}, stream=True)
], stream=False, temperature=1, top_p=1)
async for event in event_stream:
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
asyncio.run(main())
```
<!-- End Authentication [security] -->
<!-- No Authentication [security] -->
<!-- Start Available Resources and Operations [operations] -->
## Available Resources and Operations
<!-- No Available Resources and Operations [operations] -->
<details open>
<summary>Available methods</summary>
<!-- No Standalone functions [standalone-funcs] -->
### [chat](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/docs/sdks/chat/README.md)
<!-- No React hooks with TanStack Query [react-query] -->
<!-- No Server-sent event streaming [eventstream] -->
<!-- No Retries [retries] -->
<!-- No Error Handling [errors] -->
<!-- No Server Selection [server] -->
<!-- No Custom HTTP Client [http-client] -->
<!-- Start Pagination [pagination] -->
## Pagination
Some of the endpoints in this SDK support pagination. To use pagination, you make your SDK calls as usual, but the
returned response object will have a `Next` method that can be called to pull down the next group of results. If the
return value of `Next` is `None`, then there are no more pages to be fetched.
Here's an example of one such pagination call:
```python
from openrouter import OpenRouter
import os
* [complete](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/docs/sdks/chat/README.md#complete) - Create a chat completion
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:
</details>
<!-- End Available Resources and Operations [operations] -->
res = open_router.byok.list()
<!-- Start Server-sent event streaming [eventstream] -->
## Server-sent event streaming
while res is not None:
# Handle items
[Server-sent events][mdn-sse] are used to stream content from certain
operations. These operations will expose the stream as [Generator][generator] that
can be consumed using a simple `for` loop. The loop will
terminate when the server no longer has any events to send and closes the
underlying connection.
res = res.next()
```
<!-- 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.
>
The stream is also a [Context Manager][context-manager] and can be used with the `with` statement and will close the
underlying connection when the context is exited.
```python
from openrouter import OpenRouter
@@ -215,22 +245,304 @@ 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"),
})
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
# Handle response
print(res)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
<!-- End File uploads [file-upload] -->
[mdn-sse]: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events
[generator]: https://book.pythontips.com/en/latest/generators.html
[context-manager]: https://book.pythontips.com/en/latest/context_managers.html
<!-- End Server-sent event streaming [eventstream] -->
<!-- Start Retries [retries] -->
## Retries
Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.
To change the default retry strategy for a single API call, simply provide a `RetryConfig` object to the call:
```python
from openrouter import OpenRouter
from openrouter.utils import BackoffStrategy, RetryConfig
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1,
RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False))
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
If you'd like to override the default retry strategy for all operations that support retries, you can use the `retry_config` optional parameter when initializing the SDK:
```python
from openrouter import OpenRouter
from openrouter.utils import BackoffStrategy, RetryConfig
import os
with OpenRouter(
retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
<!-- End Retries [retries] -->
<!-- Start Error Handling [errors] -->
## Error Handling
[`OpenRouterError`](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/./src/openrouter/errors/openroutererror.py) is the base class for all HTTP error responses. It has the following properties:
| Property | Type | Description |
| ------------------ | ---------------- | --------------------------------------------------------------------------------------- |
| `err.message` | `str` | Error message |
| `err.status_code` | `int` | HTTP response status code eg `404` |
| `err.headers` | `httpx.Headers` | HTTP response headers |
| `err.body` | `str` | HTTP body. Can be empty string if no body is returned. |
| `err.raw_response` | `httpx.Response` | Raw HTTP response |
| `err.data` | | Optional. Some errors may contain structured data. [See Error Classes](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/#error-classes). |
### Example
```python
from openrouter import OpenRouter, errors
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = None
try:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
except errors.OpenRouterError as e:
# The base class for HTTP error responses
print(e.message)
print(e.status_code)
print(e.body)
print(e.headers)
print(e.raw_response)
# Depending on the method different errors may be thrown
if isinstance(e, errors.ChatCompletionError):
print(e.data.error) # models.Error
```
### Error Classes
**Primary errors:**
* [`OpenRouterError`](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/./src/openrouter/errors/openroutererror.py): The base class for HTTP error responses.
* [`ChatCompletionError`](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/./src/openrouter/errors/chatcompletionerror.py): Chat completion error response.
<details><summary>Less common errors (5)</summary>
<br />
**Network errors:**
* [`httpx.RequestError`](https://www.python-httpx.org/exceptions/#httpx.RequestError): Base class for request errors.
* [`httpx.ConnectError`](https://www.python-httpx.org/exceptions/#httpx.ConnectError): HTTP client was unable to make a request to a server.
* [`httpx.TimeoutException`](https://www.python-httpx.org/exceptions/#httpx.TimeoutException): HTTP request timed out.
**Inherit from [`OpenRouterError`](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/./src/openrouter/errors/openroutererror.py)**:
* [`ResponseValidationError`](https://github.com/speakeasy-sdks/openrouter-python-sdk/blob/master/./src/openrouter/errors/responsevalidationerror.py): Type mismatch between the response data and the expected Pydantic model. Provides access to the Pydantic validation error via the `cause` attribute.
</details>
<!-- End Error Handling [errors] -->
<!-- Start Server Selection [server] -->
## Server Selection
### Server Variables
The default server `https://{provider_url}/api/v1` contains variables and is set to `https://openrouter.ai/api/v1` by default. To override default values, the following parameters are available when initializing the SDK client instance:
| Variable | Parameter | Default | Description |
| -------------- | ------------------- | ----------------- | ----------- |
| `provider_url` | `provider_url: str` | `"openrouter.ai"` | |
#### Example
```python
from openrouter import OpenRouter
import os
with OpenRouter(
provider_url="https://ruddy-guacamole.info/"
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
### Override Server URL Per-Client
The default server can be overridden globally by passing a URL to the `server_url: str` optional parameter when initializing the SDK client instance. For example:
```python
from openrouter import OpenRouter
import os
with OpenRouter(
server_url="https://openrouter.ai/api/v1",
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
<!-- End Server Selection [server] -->
<!-- Start Custom HTTP Client [http-client] -->
## Custom HTTP Client
The Python SDK makes API calls using the [httpx](https://www.python-httpx.org/) HTTP library. In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with your own HTTP client instance.
Depending on whether you are using the sync or async version of the SDK, you can pass an instance of `HttpClient` or `AsyncHttpClient` respectively, which are Protocol's ensuring that the client has the necessary methods to make API calls.
This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance of `httpx.Client` or `httpx.AsyncClient` directly.
For example, you could specify a header for every request that this sdk makes as follows:
```python
from openrouter import OpenRouter
import httpx
http_client = httpx.Client(headers={"x-custom-header": "someValue"})
s = OpenRouter(client=http_client)
```
or you could wrap the client with your own custom logic:
```python
from openrouter import OpenRouter
from openrouter.httpclient import AsyncHttpClient
import httpx
class CustomClient(AsyncHttpClient):
client: AsyncHttpClient
def __init__(self, client: AsyncHttpClient):
self.client = client
async def send(
self,
request: httpx.Request,
*,
stream: bool = False,
auth: Union[
httpx._types.AuthTypes, httpx._client.UseClientDefault, None
] = httpx.USE_CLIENT_DEFAULT,
follow_redirects: Union[
bool, httpx._client.UseClientDefault
] = httpx.USE_CLIENT_DEFAULT,
) -> httpx.Response:
request.headers["Client-Level-Header"] = "added by client"
return await self.client.send(
request, stream=stream, auth=auth, follow_redirects=follow_redirects
)
def build_request(
self,
method: str,
url: httpx._types.URLTypes,
*,
content: Optional[httpx._types.RequestContent] = None,
data: Optional[httpx._types.RequestData] = None,
files: Optional[httpx._types.RequestFiles] = None,
json: Optional[Any] = None,
params: Optional[httpx._types.QueryParamTypes] = None,
headers: Optional[httpx._types.HeaderTypes] = None,
cookies: Optional[httpx._types.CookieTypes] = None,
timeout: Union[
httpx._types.TimeoutTypes, httpx._client.UseClientDefault
] = httpx.USE_CLIENT_DEFAULT,
extensions: Optional[httpx._types.RequestExtensions] = None,
) -> httpx.Request:
return self.client.build_request(
method,
url,
content=content,
data=data,
files=files,
json=json,
params=params,
headers=headers,
cookies=cookies,
timeout=timeout,
extensions=extensions,
)
s = OpenRouter(async_client=CustomClient(httpx.AsyncClient()))
```
<!-- End Custom HTTP Client [http-client] -->
<!-- Start Resource Management [resource-management] -->
## Resource Management
@@ -245,9 +557,6 @@ import os
def main():
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:
# Rest of application here...
@@ -257,9 +566,6 @@ def main():
async def amain():
async 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:
# Rest of application here...
@@ -287,26 +593,15 @@ You can also enable a default debug logger by setting an environment variable `O
# Development
## Running Tests
## Maturity
To run the test suite, you'll need to set up your environment with an OpenRouter API key.
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.
### Local Development
## Contributions
1. Copy the example environment file:
While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation.
We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.
```bash
cp .env.example .env
```
2. Edit `.env` and add your OpenRouter API key:
```bash
OPENROUTER_API_KEY=your_api_key_here
```
3. Run the tests:
```bash
pytest
```
### SDK Created by [Speakeasy](https://www.speakeasy.com/?utm_source=open-router&utm_campaign=python)
+411 -116
View File
@@ -1,16 +1,50 @@
# 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 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).
<!-- No Summary [summary] -->
<div align="center">
<img width="500" height="300" alt="image" src="https://github.com/user-attachments/assets/19d8ad52-cb56-4f87-8bce-9a9c2233ac16" />
<h1>OpenRouter Python SDK</h1>
<p>Developer-friendly Python SDK specifically catered to leverage the <strong>OpenRouter</strong> API.</p>
<a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge" /></a>
</div>
<!-- No Table of Contents [toc] -->
<!-- Start Summary [summary] -->
## Summary
OpenRouter Chat Completions API: OpenAI-compatible Chat Completions API with additional OpenRouter features
For more information about the API: [OpenRouter Documentation](https://openrouter.ai/docs)
<!-- End Summary [summary] -->
<!-- Start Table of Contents [toc] -->
## Table of Contents
<!-- $toc-max-depth=2 -->
* [SDK Installation](#sdk-installation)
* [IDE Support](#ide-support)
* [SDK Example Usage](#sdk-example-usage)
* [Authentication](#authentication)
* [Available Resources and Operations](#available-resources-and-operations)
* [Server-sent event streaming](#server-sent-event-streaming)
* [Retries](#retries)
* [Error Handling](#error-handling)
* [Server Selection](#server-selection)
* [Custom HTTP Client](#custom-http-client)
* [Resource Management](#resource-management)
* [Debugging](#debugging)
* [Development](#development)
* [Maturity](#maturity)
* [Contributions](#contributions)
<!-- End Table of Contents [toc] -->
<!-- Start SDK Installation [installation] -->
## SDK Installation
> [!TIP]
> To finish publishing your SDK to PyPI you must [run your first generation action](https://www.speakeasy.com/docs/github-setup#step-by-step-guide).
> [!NOTE]
> **Python version upgrade policy**
>
@@ -23,7 +57,7 @@ The SDK can be installed with *uv*, *pip*, or *poetry* package managers.
*uv* is a fast Python package installer and resolver, designed as a drop-in replacement for pip and pip-tools. It's recommended for its speed and modern Python tooling capabilities.
```bash
uv add openrouter
uv add git+https://github.com/speakeasy-sdks/openrouter-python-sdk.git
```
### PIP
@@ -31,7 +65,7 @@ uv add openrouter
*PIP* is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.
```bash
pip install openrouter
pip install git+https://github.com/speakeasy-sdks/openrouter-python-sdk.git
```
### Poetry
@@ -39,7 +73,7 @@ pip install openrouter
*Poetry* is a modern tool that simplifies dependency management and package publishing by using a single `pyproject.toml` file to handle project metadata and dependencies.
```bash
poetry add openrouter
poetry add git+https://github.com/speakeasy-sdks/openrouter-python-sdk.git
```
### Shell and script usage with `uv`
@@ -74,12 +108,6 @@ Once that is saved to a file, you can run it with `uv run script.py` where
`script.py` can be replaced with the actual file name.
<!-- End SDK Installation [installation] -->
<!-- Start Requirements [requirements] -->
## Requirements
This SDK requires Python 3.9 or higher. For Python version support policy, see the SDK Installation section above.
<!-- End Requirements [requirements] -->
<!-- Start IDE Support [idesupport] -->
## IDE Support
@@ -90,8 +118,10 @@ Generally, the SDK will work well with most IDEs out of the box. However, when u
- [PyCharm Pydantic Plugin](https://docs.pydantic.dev/latest/integrations/pycharm/)
<!-- End IDE Support [idesupport] -->
<!-- No SDK Example Usage [usage] -->
## SDK Usage
<!-- Start SDK Example Usage [usage] -->
## SDK Example Usage
### Example
```python
# Synchronous Example
@@ -103,25 +133,22 @@ with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.send(messages=[
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], model="anthropic/claude-4.5-sonnet", provider={
"zdr": True,
"sort": "price",
}, stream=True)
], stream=False, temperature=1, top_p=1)
for event in event_stream:
# handle event
print(event, flush=True)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
</br>
The same SDK client can also be used to make asynchronous requests by importing asyncio.
```python
# Asynchronous Example
import asyncio
@@ -134,80 +161,83 @@ async def main():
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = await open_router.chat.send_async(messages=[
res = await open_router.chat.complete_async(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
async with res as event_stream:
async for event in event_stream:
# handle event
print(event, flush=True)
asyncio.run(main())
```
<!-- End SDK Example Usage [usage] -->
<!-- Start Authentication [security] -->
## Authentication
### Per-Client Security Schemes
This SDK supports the following security scheme globally:
| Name | Type | Scheme | Environment Variable |
| --------- | ---- | ----------- | -------------------- |
| `api_key` | http | HTTP Bearer | `OPENROUTER_API_KEY` |
To authenticate with the API the `api_key` parameter must be set when initializing the SDK client instance. For example:
```python
from openrouter import OpenRouter
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], model="anthropic/claude-4.5-sonnet", provider={
"zdr": True,
"sort": "price",
}, stream=True)
], stream=False, temperature=1, top_p=1)
async for event in event_stream:
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
asyncio.run(main())
```
<!-- End Authentication [security] -->
<!-- No Authentication [security] -->
<!-- Start Available Resources and Operations [operations] -->
## Available Resources and Operations
<!-- No Available Resources and Operations [operations] -->
<details open>
<summary>Available methods</summary>
<!-- No Standalone functions [standalone-funcs] -->
### [chat](docs/sdks/chat/README.md)
<!-- No React hooks with TanStack Query [react-query] -->
<!-- No Server-sent event streaming [eventstream] -->
<!-- No Retries [retries] -->
<!-- No Error Handling [errors] -->
<!-- No Server Selection [server] -->
<!-- No Custom HTTP Client [http-client] -->
<!-- Start Pagination [pagination] -->
## Pagination
Some of the endpoints in this SDK support pagination. To use pagination, you make your SDK calls as usual, but the
returned response object will have a `Next` method that can be called to pull down the next group of results. If the
return value of `Next` is `None`, then there are no more pages to be fetched.
Here's an example of one such pagination call:
```python
from openrouter import OpenRouter
import os
* [complete](docs/sdks/chat/README.md#complete) - Create a chat completion
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:
</details>
<!-- End Available Resources and Operations [operations] -->
res = open_router.byok.list()
<!-- Start Server-sent event streaming [eventstream] -->
## Server-sent event streaming
while res is not None:
# Handle items
[Server-sent events][mdn-sse] are used to stream content from certain
operations. These operations will expose the stream as [Generator][generator] that
can be consumed using a simple `for` loop. The loop will
terminate when the server no longer has any events to send and closes the
underlying connection.
res = res.next()
```
<!-- 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.
>
The stream is also a [Context Manager][context-manager] and can be used with the `with` statement and will close the
underlying connection when the context is exited.
```python
from openrouter import OpenRouter
@@ -215,22 +245,304 @@ 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"),
})
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
# Handle response
print(res)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
<!-- End File uploads [file-upload] -->
[mdn-sse]: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events
[generator]: https://book.pythontips.com/en/latest/generators.html
[context-manager]: https://book.pythontips.com/en/latest/context_managers.html
<!-- End Server-sent event streaming [eventstream] -->
<!-- Start Retries [retries] -->
## Retries
Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.
To change the default retry strategy for a single API call, simply provide a `RetryConfig` object to the call:
```python
from openrouter import OpenRouter
from openrouter.utils import BackoffStrategy, RetryConfig
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1,
RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False))
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
If you'd like to override the default retry strategy for all operations that support retries, you can use the `retry_config` optional parameter when initializing the SDK:
```python
from openrouter import OpenRouter
from openrouter.utils import BackoffStrategy, RetryConfig
import os
with OpenRouter(
retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
<!-- End Retries [retries] -->
<!-- Start Error Handling [errors] -->
## Error Handling
[`OpenRouterError`](./src/openrouter/errors/openroutererror.py) is the base class for all HTTP error responses. It has the following properties:
| Property | Type | Description |
| ------------------ | ---------------- | --------------------------------------------------------------------------------------- |
| `err.message` | `str` | Error message |
| `err.status_code` | `int` | HTTP response status code eg `404` |
| `err.headers` | `httpx.Headers` | HTTP response headers |
| `err.body` | `str` | HTTP body. Can be empty string if no body is returned. |
| `err.raw_response` | `httpx.Response` | Raw HTTP response |
| `err.data` | | Optional. Some errors may contain structured data. [See Error Classes](#error-classes). |
### Example
```python
from openrouter import OpenRouter, errors
import os
with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = None
try:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
except errors.OpenRouterError as e:
# The base class for HTTP error responses
print(e.message)
print(e.status_code)
print(e.body)
print(e.headers)
print(e.raw_response)
# Depending on the method different errors may be thrown
if isinstance(e, errors.ChatCompletionError):
print(e.data.error) # models.Error
```
### Error Classes
**Primary errors:**
* [`OpenRouterError`](./src/openrouter/errors/openroutererror.py): The base class for HTTP error responses.
* [`ChatCompletionError`](./src/openrouter/errors/chatcompletionerror.py): Chat completion error response.
<details><summary>Less common errors (5)</summary>
<br />
**Network errors:**
* [`httpx.RequestError`](https://www.python-httpx.org/exceptions/#httpx.RequestError): Base class for request errors.
* [`httpx.ConnectError`](https://www.python-httpx.org/exceptions/#httpx.ConnectError): HTTP client was unable to make a request to a server.
* [`httpx.TimeoutException`](https://www.python-httpx.org/exceptions/#httpx.TimeoutException): HTTP request timed out.
**Inherit from [`OpenRouterError`](./src/openrouter/errors/openroutererror.py)**:
* [`ResponseValidationError`](./src/openrouter/errors/responsevalidationerror.py): Type mismatch between the response data and the expected Pydantic model. Provides access to the Pydantic validation error via the `cause` attribute.
</details>
<!-- End Error Handling [errors] -->
<!-- Start Server Selection [server] -->
## Server Selection
### Server Variables
The default server `https://{provider_url}/api/v1` contains variables and is set to `https://openrouter.ai/api/v1` by default. To override default values, the following parameters are available when initializing the SDK client instance:
| Variable | Parameter | Default | Description |
| -------------- | ------------------- | ----------------- | ----------- |
| `provider_url` | `provider_url: str` | `"openrouter.ai"` | |
#### Example
```python
from openrouter import OpenRouter
import os
with OpenRouter(
provider_url="https://ruddy-guacamole.info/"
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
### Override Server URL Per-Client
The default server can be overridden globally by passing a URL to the `server_url: str` optional parameter when initializing the SDK client instance. For example:
```python
from openrouter import OpenRouter
import os
with OpenRouter(
server_url="https://openrouter.ai/api/v1",
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
<!-- End Server Selection [server] -->
<!-- Start Custom HTTP Client [http-client] -->
## Custom HTTP Client
The Python SDK makes API calls using the [httpx](https://www.python-httpx.org/) HTTP library. In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with your own HTTP client instance.
Depending on whether you are using the sync or async version of the SDK, you can pass an instance of `HttpClient` or `AsyncHttpClient` respectively, which are Protocol's ensuring that the client has the necessary methods to make API calls.
This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance of `httpx.Client` or `httpx.AsyncClient` directly.
For example, you could specify a header for every request that this sdk makes as follows:
```python
from openrouter import OpenRouter
import httpx
http_client = httpx.Client(headers={"x-custom-header": "someValue"})
s = OpenRouter(client=http_client)
```
or you could wrap the client with your own custom logic:
```python
from openrouter import OpenRouter
from openrouter.httpclient import AsyncHttpClient
import httpx
class CustomClient(AsyncHttpClient):
client: AsyncHttpClient
def __init__(self, client: AsyncHttpClient):
self.client = client
async def send(
self,
request: httpx.Request,
*,
stream: bool = False,
auth: Union[
httpx._types.AuthTypes, httpx._client.UseClientDefault, None
] = httpx.USE_CLIENT_DEFAULT,
follow_redirects: Union[
bool, httpx._client.UseClientDefault
] = httpx.USE_CLIENT_DEFAULT,
) -> httpx.Response:
request.headers["Client-Level-Header"] = "added by client"
return await self.client.send(
request, stream=stream, auth=auth, follow_redirects=follow_redirects
)
def build_request(
self,
method: str,
url: httpx._types.URLTypes,
*,
content: Optional[httpx._types.RequestContent] = None,
data: Optional[httpx._types.RequestData] = None,
files: Optional[httpx._types.RequestFiles] = None,
json: Optional[Any] = None,
params: Optional[httpx._types.QueryParamTypes] = None,
headers: Optional[httpx._types.HeaderTypes] = None,
cookies: Optional[httpx._types.CookieTypes] = None,
timeout: Union[
httpx._types.TimeoutTypes, httpx._client.UseClientDefault
] = httpx.USE_CLIENT_DEFAULT,
extensions: Optional[httpx._types.RequestExtensions] = None,
) -> httpx.Request:
return self.client.build_request(
method,
url,
content=content,
data=data,
files=files,
json=json,
params=params,
headers=headers,
cookies=cookies,
timeout=timeout,
extensions=extensions,
)
s = OpenRouter(async_client=CustomClient(httpx.AsyncClient()))
```
<!-- End Custom HTTP Client [http-client] -->
<!-- Start Resource Management [resource-management] -->
## Resource Management
@@ -245,9 +557,6 @@ import os
def main():
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:
# Rest of application here...
@@ -257,9 +566,6 @@ def main():
async def amain():
async 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:
# Rest of application here...
@@ -287,26 +593,15 @@ You can also enable a default debug logger by setting an environment variable `O
# Development
## Running Tests
## Maturity
To run the test suite, you'll need to set up your environment with an OpenRouter API key.
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.
### Local Development
## Contributions
1. Copy the example environment file:
While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation.
We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.
```bash
cp .env.example .env
```
2. Edit `.env` and add your OpenRouter API key:
```bash
OPENROUTER_API_KEY=your_api_key_here
```
3. Run the tests:
```bash
pytest
```
### SDK Created by [Speakeasy](https://www.speakeasy.com/?utm_source=open-router&utm_campaign=python)
+6 -60
View File
@@ -1,71 +1,17 @@
## 2025-11-15 18:16:18
## 2025-08-22 15:59:18
### Changes
Based on:
- OpenAPI Doc
- Speakeasy CLI 1.658.1 (2.755.6) https://github.com/speakeasy-api/speakeasy
- Speakeasy CLI 1.606.2 (2.687.1) https://github.com/speakeasy-api/speakeasy
### Generated
- [python v0.0.16] .
### Releases
- [PyPI v0.0.16] https://pypi.org/project/openrouter/0.0.16 - .
- [python v0.1.3] .
## 2026-06-11 00:55:55
## 2025-09-17 00:07:51
### Changes
Based on:
- OpenAPI Doc
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
- Speakeasy CLI 1.617.1 (2.701.8) https://github.com/speakeasy-api/speakeasy
### Generated
- [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 - .
- [python v0.6.3] .
+20 -13
View File
@@ -6,22 +6,25 @@ 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.analytics.get_user_activity()
res = open_router.chat.complete(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
# Handle response
print(res)
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
```
</br>
The same SDK client can also be used to make asynchronous requests by importing asyncio.
```python
# Asynchronous Example
import asyncio
@@ -31,16 +34,20 @@ import os
async def main():
async 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 = await open_router.analytics.get_user_activity_async()
res = await open_router.chat.complete_async(messages=[
{
"role": "user",
"content": "Hello, how are you?",
},
], stream=False, temperature=1, top_p=1)
# Handle response
print(res)
async with res as event_stream:
async for event in event_stream:
# handle event
print(event, flush=True)
asyncio.run(main())
```
BIN
View File
Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.1 MiB

-10
View File
@@ -1,10 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="400" viewBox="0 0 1200 400">
<title>OpenRouter</title>
<path fill="currentColor" d="M431.4 196.2c0 11.2-2.1 20.8-6.2 28.8a45 45 0 0 1-41 25 44.8 44.8 0 0 1-41-25c-4.2-8-6.2-17.7-6.2-28.8 0-11.2 2-20.8 6.1-28.8a44.9 44.9 0 0 1 41.1-25 45 45 0 0 1 41 25c4.1 8 6.2 17.6 6.2 28.8m-15.7 0c0-8.5-1.4-15.7-4.1-21.6a30.6 30.6 0 0 0-11.3-13.3c-4.7-3-10.1-4.5-16.1-4.5a30 30 0 0 0-16.2 4.5c-4.7 3-8.4 7.5-11.2 13.3-2.7 5.9-4.1 13-4.1 21.6 0 8.5 1.4 15.7 4.1 21.5A30.7 30.7 0 0 0 368 231c4.8 3 10.2 4.6 16.2 4.6s11.4-1.5 16.1-4.6c4.8-3 8.5-7.4 11.3-13.3 2.7-5.8 4.1-13 4.1-21.5Zm34 81.8V170h15v12.7h1.3c.9-1.6 2.1-3.5 3.8-5.6a22 22 0 0 1 18.7-8.1 30.6 30.6 0 0 1 28.7 18.6c2.9 6 4.3 13.3 4.3 21.8s-1.4 15.8-4.2 21.8a33 33 0 0 1-11.7 14 30 30 0 0 1-17 4.9c-4.7 0-8.6-.8-11.6-2.4a22 22 0 0 1-7.1-5.6c-1.7-2.2-3-4.1-4-5.8h-.8V278h-15.3m15-68.7c0 5.5.7 10.3 2.3 14.5 1.6 4.2 4 7.4 7 9.7 3 2.4 6.7 3.5 11.1 3.5 4.6 0 8.4-1.2 11.5-3.6 3-2.5 5.4-5.8 7-10 1.6-4.2 2.4-8.9 2.4-14.1 0-5.2-.8-9.9-2.4-14a21.7 21.7 0 0 0-7-9.7 18 18 0 0 0-11.5-3.6c-4.4 0-8.1 1.1-11.2 3.4-3 2.3-5.3 5.5-7 9.6a40 40 0 0 0-2.3 14.3ZM572.4 250c-7.8 0-14.4-1.6-20-5-5.6-3.3-9.9-8-12.9-14s-4.5-13.2-4.5-21.3c0-8 1.5-15.1 4.5-21.3a35 35 0 0 1 12.7-14.4 38.5 38.5 0 0 1 32-3 31.3 31.3 0 0 1 19 19.2c2 5 2.9 11 2.9 18.2v5.4h-62.5v-11.5h47.5c0-4-.8-7.6-2.5-10.7a18.6 18.6 0 0 0-17.2-10c-4.3 0-8 1-11.2 3a22.3 22.3 0 0 0-10 19.2v9c0 5.2 1 9.6 2.8 13.3 1.9 3.7 4.5 6.5 7.8 8.4a23 23 0 0 0 11.7 2.9c3 0 5.6-.4 8-1.3a16.4 16.4 0 0 0 10.2-10l14.4 2.7c-1.1 4.3-3.2 8-6.2 11.2-3 3.2-6.7 5.6-11.2 7.4a41.7 41.7 0 0 1-15.3 2.6Zm66-48.2v46.7h-15.3V170H638v12.8h1c1.8-4.2 4.6-7.5 8.5-10 3.8-2.6 8.7-3.8 14.6-3.8 5.4 0 10 1.1 14 3.3 4.1 2.3 7.2 5.6 9.4 10a36 36 0 0 1 3.4 16.3v50h-15.3v-48.2a19 19 0 0 0-4.5-13.3c-3-3.3-7-4.9-12.2-4.9a19 19 0 0 0-9.4 2.3 16.4 16.4 0 0 0-6.5 6.8 21.8 21.8 0 0 0-2.4 10.6Zm72 46.7V143.8h37.3c8 0 14.8 1.4 20.2 4.2 5.4 2.8 9.4 6.7 12 11.6a35 35 0 0 1 4 17c0 6.5-1.3 12.1-4 17a27.3 27.3 0 0 1-12 11.3c-5.4 2.7-12.2 4-20.3 4h-28.2v-13.6h26.8c5.1 0 9.3-.7 12.5-2.2 3.2-1.4 5.6-3.6 7-6.4a21 21 0 0 0 2.3-10c0-4-.7-7.4-2.2-10.3a15.2 15.2 0 0 0-7.1-6.7 29.3 29.3 0 0 0-12.7-2.3h-19.9v91.2h-15.7m51.7-47.3 25.8 47.3h-18l-25.3-47.3h17.5Zm73 48.8a34.1 34.1 0 0 1-32-19.2 47 47 0 0 1-4.6-21.3c0-8.1 1.5-15.2 4.5-21.3a34.1 34.1 0 0 1 32-19.3 34.1 34.1 0 0 1 32 19.3 45 45 0 0 1 4.7 21.3 47 47 0 0 1-4.6 21.3 34.1 34.1 0 0 1-32 19.2m0-12.8c4.8 0 8.8-1.3 11.9-3.8 3.1-2.5 5.4-5.9 7-10a42 42 0 0 0 2.2-14c0-5-.7-9.5-2.2-13.8a22.8 22.8 0 0 0-7-10.1 18.2 18.2 0 0 0-11.9-3.8c-4.8 0-8.8 1.2-12 3.8-3 2.6-5.4 6-7 10.2a40.5 40.5 0 0 0-2.2 13.8c0 5 .8 9.6 2.3 13.8 1.5 4.2 3.8 7.6 7 10.1 3.1 2.5 7.1 3.8 12 3.8ZM938.6 216v-46h15.3v78.6h-15v-13.7h-.8a24.4 24.4 0 0 1-23.5 14.7 26 26 0 0 1-13.4-3.4 23 23 0 0 1-9-10 36.3 36.3 0 0 1-3.4-16.2v-50h15.3v48.1a18 18 0 0 0 4.4 12.8c3 3.2 6.9 4.8 11.6 4.8a19 19 0 0 0 15.7-8.7c1.9-2.9 2.8-6.6 2.8-11Zm72.5-46v12.3h-43V170h43m-31.4-18.8H995v74.3c0 3 .4 5.2 1.3 6.7.9 1.4 2 2.5 3.5 3 1.4.5 3 .8 4.6.8a176.6 176.6 0 0 0 5.4-.7l2.7 12.6a27.2 27.2 0 0 1-10 1.7c-4 0-7.7-.7-11.2-2.2a19.3 19.3 0 0 1-8.4-7c-2.1-3-3.2-7-3.2-11.7v-77.5Zm82.1 99c-7.7 0-14.4-1.7-20-5-5.5-3.4-9.8-8-12.8-14.1-3-6-4.6-13.2-4.6-21.3a47 47 0 0 1 4.6-21.3c3-6.1 7.2-11 12.6-14.4a38.5 38.5 0 0 1 32-3 31.3 31.3 0 0 1 19 19.2c2 5 3 11 3 18.2v5.4H1033v-11.5h47.4c0-4-.8-7.6-2.4-10.7a18.7 18.7 0 0 0-17.3-10c-4.3 0-8 1-11.2 3a22.9 22.9 0 0 0-9.9 19.2v9c0 5.2.9 9.6 2.8 13.3 1.8 3.7 4.4 6.5 7.8 8.4a23 23 0 0 0 11.7 2.9 24 24 0 0 0 7.9-1.3 16.7 16.7 0 0 0 10.2-9.9l14.4 2.6a26 26 0 0 1-6.2 11.2 30 30 0 0 1-11.2 7.4 41.6 41.6 0 0 1-15.3 2.6Zm50.7-1.6V170h14.8v12.5h.8c1.5-4.2 4-7.6 7.6-10 3.7-2.5 7.8-3.7 12.4-3.7a68 68 0 0 1 6.5.4v14.6a31.9 31.9 0 0 0-8-1 20 20 0 0 0-9.6 2.4 17.2 17.2 0 0 0-9.2 15.4v48h-15.3Z"/>
<g fill="currentColor" stroke="currentColor">
<path stroke-width="35.3" d="M46.2 200.5c5.9 0 28.6-5.1 40.3-11.8 11.8-6.6 11.8-6.6 36.1-23.9 30.8-21.8 52.5-14.5 88.2-14.5"/>
<path stroke-width=".4" d="M245.3 150.5 185 185.3v-69.6l60.3 34.8Z"/>
<path stroke-width="35.3" d="M45 200.5c5.9 0 28.6 5 40.4 11.7 11.7 6.7 11.7 6.7 36 24 30.8 21.8 52.5 14.5 88.2 14.5"/>
<path stroke-width=".4" d="m244.1 250.4-60.3-34.7v69.5l60.3-34.8Z"/>
</g>
</svg>

Before

Width:  |  Height:  |  Size: 4.2 KiB

-18
View File
@@ -1,18 +0,0 @@
# ActivityItem
## Fields
| Field | Type | Required | Description | Example |
| --------------------------------------------------- | --------------------------------------------------- | --------------------------------------------------- | --------------------------------------------------- | --------------------------------------------------- |
| `byok_usage_inference` | *float* | :heavy_check_mark: | BYOK inference cost in USD (external credits spent) | 0.012 |
| `completion_tokens` | *int* | :heavy_check_mark: | Total completion tokens generated | 125 |
| `date_` | *str* | :heavy_check_mark: | Date of the activity (YYYY-MM-DD format) | 2025-08-24 |
| `endpoint_id` | *str* | :heavy_check_mark: | Unique identifier for the endpoint | 550e8400-e29b-41d4-a716-446655440000 |
| `model` | *str* | :heavy_check_mark: | Model slug (e.g., "openai/gpt-4.1") | openai/gpt-4.1 |
| `model_permaslug` | *str* | :heavy_check_mark: | Model permaslug (e.g., "openai/gpt-4.1-2025-04-14") | openai/gpt-4.1-2025-04-14 |
| `prompt_tokens` | *int* | :heavy_check_mark: | Total prompt tokens used | 50 |
| `provider_name` | *str* | :heavy_check_mark: | Name of the provider serving this endpoint | OpenAI |
| `reasoning_tokens` | *int* | :heavy_check_mark: | Total reasoning tokens used | 25 |
| `requests` | *int* | :heavy_check_mark: | Number of requests made | 5 |
| `usage` | *float* | :heavy_check_mark: | Total cost in USD (OpenRouter credits spent) | 0.015 |
-14
View File
@@ -1,14 +0,0 @@
# Architecture
Model architecture information
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------ | ------------------------------------------------------------------ | ------------------------------------------------------------------ | ------------------------------------------------------------------ | ------------------------------------------------------------------ |
| `input_modalities` | List[[components.InputModality](../components/inputmodality.md)] | :heavy_check_mark: | Supported input modalities | |
| `instruct_type` | [Nullable[components.InstructType]](../components/instructtype.md) | :heavy_check_mark: | Instruction format type | chatml |
| `modality` | *Nullable[str]* | :heavy_check_mark: | Primary modality of the model | text |
| `output_modalities` | List[[components.OutputModality](../components/outputmodality.md)] | :heavy_check_mark: | Supported output modalities | |
| `tokenizer` | [Nullable[components.Tokenizer]](../components/tokenizer.md) | :heavy_check_mark: | N/A | GPT |
@@ -1,12 +0,0 @@
# BadGatewayResponseErrorData
Error data for BadGatewayResponse
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `code` | *int* | :heavy_check_mark: | N/A |
| `message` | *str* | :heavy_check_mark: | N/A |
| `metadata` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
@@ -1,12 +0,0 @@
# BadRequestResponseErrorData
Error data for BadRequestResponse
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `code` | *int* | :heavy_check_mark: | N/A |
| `message` | *str* | :heavy_check_mark: | N/A |
| `metadata` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
-13
View File
@@ -1,13 +0,0 @@
# By
The provider sorting strategy (price, throughput, latency)
## Values
| Name | Value |
| ------------ | ------------ |
| `PRICE` | price |
| `THROUGHPUT` | throughput |
| `LATENCY` | latency |
| `EXACTO` | exacto |
-10
View File
@@ -1,10 +0,0 @@
# ChatStreamOptions
Streaming configuration options
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| ~~`include_usage`~~ | *Optional[bool]* | :heavy_minus_sign: | : warning: ** DEPRECATED **: This will be removed in a future release, please migrate away from it as soon as possible.<br/><br/>Deprecated: This field has no effect. Full usage details are always included. | true |
-25
View File
@@ -1,25 +0,0 @@
# Code
## Values
| Name | Value |
| -------------------------------- | -------------------------------- |
| `SERVER_ERROR` | server_error |
| `RATE_LIMIT_EXCEEDED` | rate_limit_exceeded |
| `INVALID_PROMPT` | invalid_prompt |
| `VECTOR_STORE_TIMEOUT` | vector_store_timeout |
| `INVALID_IMAGE` | invalid_image |
| `INVALID_IMAGE_FORMAT` | invalid_image_format |
| `INVALID_BASE64_IMAGE` | invalid_base64_image |
| `INVALID_IMAGE_URL` | invalid_image_url |
| `IMAGE_TOO_LARGE` | image_too_large |
| `IMAGE_TOO_SMALL` | image_too_small |
| `IMAGE_PARSE_ERROR` | image_parse_error |
| `IMAGE_CONTENT_POLICY_VIOLATION` | image_content_policy_violation |
| `INVALID_IMAGE_MODE` | invalid_image_mode |
| `IMAGE_FILE_TOO_LARGE` | image_file_too_large |
| `UNSUPPORTED_IMAGE_MEDIA_TYPE` | unsupported_image_media_type |
| `EMPTY_IMAGE_FILE` | empty_image_file |
| `FAILED_TO_DOWNLOAD_IMAGE` | failed_to_download_image |
| `IMAGE_FILE_NOT_FOUND` | image_file_not_found |
-12
View File
@@ -1,12 +0,0 @@
# CostDetails
Breakdown of upstream inference costs
## Fields
| Field | Type | Required | Description |
| ------------------------------------- | ------------------------------------- | ------------------------------------- | ------------------------------------- |
| `upstream_inference_completions_cost` | *float* | :heavy_check_mark: | N/A |
| `upstream_inference_cost` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `upstream_inference_prompt_cost` | *float* | :heavy_check_mark: | N/A |
-15
View File
@@ -1,15 +0,0 @@
# DefaultParameters
Default parameters for this model
## Fields
| Field | Type | Required | Description |
| ------------------------- | ------------------------- | ------------------------- | ------------------------- |
| `frequency_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `presence_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `repetition_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `temperature` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `top_k` | *OptionalNullable[int]* | :heavy_minus_sign: | N/A |
| `top_p` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
@@ -1,12 +0,0 @@
# EdgeNetworkTimeoutResponseErrorData
Error data for EdgeNetworkTimeoutResponse
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `code` | *int* | :heavy_check_mark: | N/A |
| `message` | *str* | :heavy_check_mark: | N/A |
| `metadata` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
-13
View File
@@ -1,13 +0,0 @@
# EndpointStatus
## Values
| Name | Value |
| ---------- | ---------- |
| `ZERO` | 0 |
| `MINUS_1` | -1 |
| `MINUS_2` | -2 |
| `MINUS_3` | -3 |
| `MINUS_5` | -5 |
| `MINUS_10` | -10 |
-11
View File
@@ -1,11 +0,0 @@
# FileCitation
## Fields
| Field | Type | Required | Description |
| ---------------------------------------------------------------- | ---------------------------------------------------------------- | ---------------------------------------------------------------- | ---------------------------------------------------------------- |
| `file_id` | *str* | :heavy_check_mark: | N/A |
| `filename` | *str* | :heavy_check_mark: | N/A |
| `index` | *int* | :heavy_check_mark: | N/A |
| `type` | [components.FileCitationType](../components/filecitationtype.md) | :heavy_check_mark: | N/A |
-8
View File
@@ -1,8 +0,0 @@
# FileCitationType
## Values
| Name | Value |
| --------------- | --------------- |
| `FILE_CITATION` | file_citation |
-10
View File
@@ -1,10 +0,0 @@
# FilePath
## Fields
| Field | Type | Required | Description |
| -------------------------------------------------------- | -------------------------------------------------------- | -------------------------------------------------------- | -------------------------------------------------------- |
| `file_id` | *str* | :heavy_check_mark: | N/A |
| `index` | *int* | :heavy_check_mark: | N/A |
| `type` | [components.FilePathType](../components/filepathtype.md) | :heavy_check_mark: | N/A |
-8
View File
@@ -1,8 +0,0 @@
# FilePathType
## Values
| Name | Value |
| ----------- | ----------- |
| `FILE_PATH` | file_path |
@@ -1,12 +0,0 @@
# ForbiddenResponseErrorData
Error data for ForbiddenResponse
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `code` | *int* | :heavy_check_mark: | N/A |
| `message` | *str* | :heavy_check_mark: | N/A |
| `metadata` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
-11
View File
@@ -1,11 +0,0 @@
# ImageGenerationStatus
## Values
| Name | Value |
| ------------- | ------------- |
| `IN_PROGRESS` | in_progress |
| `COMPLETED` | completed |
| `GENERATING` | generating |
| `FAILED` | failed |
-12
View File
@@ -1,12 +0,0 @@
# InputModality
## Values
| Name | Value |
| ------- | ------- |
| `TEXT` | text |
| `IMAGE` | image |
| `FILE` | file |
| `AUDIO` | audio |
| `VIDEO` | video |
-8
View File
@@ -1,8 +0,0 @@
# InputTokensDetails
## Fields
| Field | Type | Required | Description |
| ------------------ | ------------------ | ------------------ | ------------------ |
| `cached_tokens` | *int* | :heavy_check_mark: | N/A |
-31
View File
@@ -1,31 +0,0 @@
# InstructType
Instruction format type
## Values
| Name | Value |
| --------------- | --------------- |
| `NONE` | none |
| `AIROBOROS` | airoboros |
| `ALPACA` | alpaca |
| `ALPACA_MODIF` | alpaca-modif |
| `CHATML` | chatml |
| `CLAUDE` | claude |
| `CODE_LLAMA` | code-llama |
| `GEMMA` | gemma |
| `LLAMA2` | llama2 |
| `LLAMA3` | llama3 |
| `MISTRAL` | mistral |
| `NEMOTRON` | nemotron |
| `NEURAL` | neural |
| `OPENCHAT` | openchat |
| `PHI3` | phi3 |
| `RWKV` | rwkv |
| `VICUNA` | vicuna |
| `ZEPHYR` | zephyr |
| `DEEPSEEK_R1` | deepseek-r1 |
| `DEEPSEEK_V3_1` | deepseek-v3.1 |
| `QWQ` | qwq |
| `QWEN3` | qwen3 |
@@ -1,12 +0,0 @@
# InternalServerResponseErrorData
Error data for InternalServerResponse
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `code` | *int* | :heavy_check_mark: | N/A |
| `message` | *str* | :heavy_check_mark: | N/A |
| `metadata` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
-15
View File
@@ -1,15 +0,0 @@
# ListEndpointsResponse
List of available endpoints for a model
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `architecture` | [components.Architecture](../components/architecture.md) | :heavy_check_mark: | N/A | {<br/>"input_modalities": [<br/>"text"<br/>],<br/>"instruct_type": "chatml",<br/>"modality": "text-\u003etext",<br/>"output_modalities": [<br/>"text"<br/>],<br/>"tokenizer": "GPT"<br/>} |
| `created` | *int* | :heavy_check_mark: | Unix timestamp of when the model was created | 1692901234 |
| `description` | *str* | :heavy_check_mark: | Description of the model | GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy. |
| `endpoints` | List[[components.PublicEndpoint](../components/publicendpoint.md)] | :heavy_check_mark: | List of available endpoints for this model | |
| `id` | *str* | :heavy_check_mark: | Unique identifier for the model | openai/gpt-4 |
| `name` | *str* | :heavy_check_mark: | Display name of the model | GPT-4 |
-10
View File
@@ -1,10 +0,0 @@
# Modality
## Values
| Name | Value |
| ------- | ------- |
| `TEXT` | text |
| `IMAGE` | image |
| `AUDIO` | audio |
-28
View File
@@ -1,28 +0,0 @@
# Model
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/>} |
| `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/>} |
-14
View File
@@ -1,14 +0,0 @@
# ModelArchitecture
Model architecture information
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ |
| `input_modalities` | List[[components.InputModality](../components/inputmodality.md)] | :heavy_check_mark: | Supported input modalities | |
| `instruct_type` | [OptionalNullable[components.ModelArchitectureInstructType]](../components/modelarchitectureinstructtype.md) | :heavy_minus_sign: | Instruction format type | chatml |
| `modality` | *Nullable[str]* | :heavy_check_mark: | Primary modality of the model | text->text |
| `output_modalities` | List[[components.OutputModality](../components/outputmodality.md)] | :heavy_check_mark: | Supported output modalities | |
| `tokenizer` | [Optional[components.ModelGroup]](../components/modelgroup.md) | :heavy_minus_sign: | Tokenizer type used by the model | GPT |
@@ -1,31 +0,0 @@
# ModelArchitectureInstructType
Instruction format type
## Values
| Name | Value |
| --------------- | --------------- |
| `NONE` | none |
| `AIROBOROS` | airoboros |
| `ALPACA` | alpaca |
| `ALPACA_MODIF` | alpaca-modif |
| `CHATML` | chatml |
| `CLAUDE` | claude |
| `CODE_LLAMA` | code-llama |
| `GEMMA` | gemma |
| `LLAMA2` | llama2 |
| `LLAMA3` | llama3 |
| `MISTRAL` | mistral |
| `NEMOTRON` | nemotron |
| `NEURAL` | neural |
| `OPENCHAT` | openchat |
| `PHI3` | phi3 |
| `RWKV` | rwkv |
| `VICUNA` | vicuna |
| `ZEPHYR` | zephyr |
| `DEEPSEEK_R1` | deepseek-r1 |
| `DEEPSEEK_V3_1` | deepseek-v3.1 |
| `QWQ` | qwq |
| `QWEN3` | qwen3 |
-29
View File
@@ -1,29 +0,0 @@
# ModelGroup
Tokenizer type used by the model
## Values
| Name | Value |
| ----------- | ----------- |
| `ROUTER` | Router |
| `MEDIA` | Media |
| `OTHER` | Other |
| `GPT` | GPT |
| `CLAUDE` | Claude |
| `GEMINI` | Gemini |
| `GEMMA` | Gemma |
| `GROK` | Grok |
| `COHERE` | Cohere |
| `NOVA` | Nova |
| `QWEN` | Qwen |
| `YI` | Yi |
| `DEEP_SEEK` | DeepSeek |
| `MISTRAL` | Mistral |
| `LLAMA2` | Llama2 |
| `LLAMA3` | Llama3 |
| `LLAMA4` | Llama4 |
| `PA_LM` | PaLM |
| `RWKV` | RWKV |
| `QWEN3` | Qwen3 |
-10
View File
@@ -1,10 +0,0 @@
# ModelsCountResponse
Model count data
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ |
| `data` | [components.ModelsCountResponseData](../components/modelscountresponsedata.md) | :heavy_check_mark: | Model count data | {<br/>"count": 150<br/>} |
-10
View File
@@ -1,10 +0,0 @@
# ModelsListResponse
List of available models
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `data` | List[[components.Model](../components/model.md)] | :heavy_check_mark: | List of available models | [<br/>{<br/>"architecture": {<br/>"input_modalities": [<br/>"text"<br/>],<br/>"instruct_type": "chatml",<br/>"modality": "text-\u003etext",<br/>"output_modalities": [<br/>"text"<br/>],<br/>"tokenizer": "GPT"<br/>},<br/>"canonical_slug": "openai/gpt-4",<br/>"context_length": 8192,<br/>"created": 1692901234,<br/>"default_parameters": null,<br/>"description": "GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy.",<br/>"expiration_date": null,<br/>"id": "openai/gpt-4",<br/>"knowledge_cutoff": null,<br/>"links": {<br/>"details": "/api/v1/models/openai/gpt-5.4/endpoints"<br/>},<br/>"name": "GPT-4",<br/>"per_request_limits": null,<br/>"pricing": {<br/>"completion": "0.00006",<br/>"image": "0",<br/>"prompt": "0.00003",<br/>"request": "0"<br/>},<br/>"supported_parameters": [<br/>"temperature",<br/>"top_p",<br/>"max_tokens"<br/>],<br/>"supported_voices": null,<br/>"top_provider": {<br/>"context_length": 8192,<br/>"is_moderated": true,<br/>"max_completion_tokens": 4096<br/>}<br/>}<br/>] |
@@ -1,12 +0,0 @@
# NotFoundResponseErrorData
Error data for NotFoundResponse
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `code` | *int* | :heavy_check_mark: | N/A |
| `message` | *str* | :heavy_check_mark: | N/A |
| `metadata` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
@@ -1,23 +0,0 @@
# OpenAIResponsesAnnotation
## Supported Types
### `components.FileCitation`
```python
value: components.FileCitation = /* values here */
```
### `components.URLCitation`
```python
value: components.URLCitation = /* values here */
```
### `components.FilePath`
```python
value: components.FilePath = /* values here */
```
@@ -1,8 +0,0 @@
# OpenAIResponsesRefusalContentType
## Values
| Name | Value |
| --------- | --------- |
| `REFUSAL` | refusal |
@@ -1,13 +0,0 @@
# OpenAIResponsesResponseStatus
## Values
| Name | Value |
| ------------- | ------------- |
| `COMPLETED` | completed |
| `INCOMPLETE` | incomplete |
| `IN_PROGRESS` | in_progress |
| `FAILED` | failed |
| `CANCELLED` | cancelled |
| `QUEUED` | queued |
@@ -1,8 +0,0 @@
# OpenAIResponsesToolChoice
## Fields
| Field | Type | Required | Description |
| ---------------------------------------- | ---------------------------------------- | ---------------------------------------- | ---------------------------------------- |
| `type` | [components.Type](../components/type.md) | :heavy_check_mark: | N/A |
@@ -1,9 +0,0 @@
# OpenAIResponsesToolChoiceFunction
## Fields
| Field | Type | Required | Description |
| ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
| `name` | *str* | :heavy_check_mark: | N/A |
| `type` | [components.OpenAIResponsesToolChoiceTypeFunction](../components/openairesponsestoolchoicetypefunction.md) | :heavy_check_mark: | N/A |
@@ -1,8 +0,0 @@
# OpenAIResponsesToolChoiceTypeWebSearchPreview
## Values
| Name | Value |
| -------------------- | -------------------- |
| `WEB_SEARCH_PREVIEW` | web_search_preview |
@@ -1,8 +0,0 @@
# OpenAIResponsesToolChoiceTypeWebSearchPreview20250311
## Values
| Name | Value |
| ------------------------------- | ------------------------------- |
| `WEB_SEARCH_PREVIEW_2025_03_11` | web_search_preview_2025_03_11 |
@@ -1,53 +0,0 @@
# OpenAIResponsesToolChoiceUnion
## Supported Types
### `components.OpenAIResponsesToolChoiceAuto`
```python
value: components.OpenAIResponsesToolChoiceAuto = /* values here */
```
### `components.OpenAIResponsesToolChoiceNone`
```python
value: components.OpenAIResponsesToolChoiceNone = /* values here */
```
### `components.OpenAIResponsesToolChoiceRequired`
```python
value: components.OpenAIResponsesToolChoiceRequired = /* values here */
```
### `components.OpenAIResponsesToolChoiceFunction`
```python
value: components.OpenAIResponsesToolChoiceFunction = /* values here */
```
### `components.OpenAIResponsesToolChoice`
```python
value: components.OpenAIResponsesToolChoice = /* values here */
```
### `components.ToolChoiceAllowed`
```python
value: components.ToolChoiceAllowed = /* values here */
```
### `components.OpenAIResponsesToolChoiceApplyPatch`
```python
value: components.OpenAIResponsesToolChoiceApplyPatch = /* values here */
```
### `components.OpenAIResponsesToolChoiceShell`
```python
value: components.OpenAIResponsesToolChoiceShell = /* values here */
```
@@ -1,9 +0,0 @@
# OpenAIResponsesTruncation
## Values
| Name | Value |
| ---------- | ---------- |
| `AUTO` | auto |
| `DISABLED` | disabled |
-13
View File
@@ -1,13 +0,0 @@
# OutputMessage
## Fields
| Field | Type | Required | Description |
| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `content` | List[[components.OutputMessageContent](../components/outputmessagecontent.md)] | :heavy_check_mark: | N/A |
| `id` | *str* | :heavy_check_mark: | N/A |
| `phase` | [OptionalNullable[components.OutputMessagePhaseUnion]](../components/outputmessagephaseunion.md) | :heavy_minus_sign: | The phase of an assistant message. Use `commentary` for an intermediate assistant message and `final_answer` for the final assistant message. For follow-up requests with models like `gpt-5.3-codex` and later, preserve and resend phase on all assistant messages. Omitting it can degrade performance. Not used for user messages. |
| `role` | [components.OutputMessageRole](../components/outputmessagerole.md) | :heavy_check_mark: | N/A |
| `status` | [Optional[components.OutputMessageStatusUnion]](../components/outputmessagestatusunion.md) | :heavy_minus_sign: | N/A |
| `type` | [components.OutputMessageType](../components/outputmessagetype.md) | :heavy_check_mark: | N/A |
-17
View File
@@ -1,17 +0,0 @@
# OutputMessageContent
## Supported Types
### `components.ResponseOutputText`
```python
value: components.ResponseOutputText = /* values here */
```
### `components.OpenAIResponsesRefusalContent`
```python
value: components.OpenAIResponsesRefusalContent = /* values here */
```
@@ -1,23 +0,0 @@
# OutputMessageStatusUnion
## Supported Types
### `components.OutputMessageStatusCompleted`
```python
value: components.OutputMessageStatusCompleted = /* values here */
```
### `components.OutputMessageStatusIncomplete`
```python
value: components.OutputMessageStatusIncomplete = /* values here */
```
### `components.OutputMessageStatusInProgress`
```python
value: components.OutputMessageStatusInProgress = /* values here */
```
-15
View File
@@ -1,15 +0,0 @@
# OutputModality
## Values
| Name | Value |
| --------------- | --------------- |
| `TEXT` | text |
| `IMAGE` | image |
| `EMBEDDINGS` | embeddings |
| `AUDIO` | audio |
| `VIDEO` | video |
| `RERANK` | rerank |
| `SPEECH` | speech |
| `TRANSCRIPTION` | transcription |
-8
View File
@@ -1,8 +0,0 @@
# OutputTokensDetails
## Fields
| Field | Type | Required | Description |
| ------------------ | ------------------ | ------------------ | ------------------ |
| `reasoning_tokens` | *int* | :heavy_check_mark: | N/A |
-32
View File
@@ -1,32 +0,0 @@
# Parameter
## Values
| Name | Value |
| ----------------------- | ----------------------- |
| `TEMPERATURE` | temperature |
| `TOP_P` | top_p |
| `TOP_K` | top_k |
| `MIN_P` | min_p |
| `TOP_A` | top_a |
| `FREQUENCY_PENALTY` | frequency_penalty |
| `PRESENCE_PENALTY` | presence_penalty |
| `REPETITION_PENALTY` | repetition_penalty |
| `MAX_TOKENS` | max_tokens |
| `MAX_COMPLETION_TOKENS` | max_completion_tokens |
| `LOGIT_BIAS` | logit_bias |
| `LOGPROBS` | logprobs |
| `TOP_LOGPROBS` | top_logprobs |
| `SEED` | seed |
| `RESPONSE_FORMAT` | response_format |
| `STRUCTURED_OUTPUTS` | structured_outputs |
| `STOP` | stop |
| `TOOLS` | tools |
| `TOOL_CHOICE` | tool_choice |
| `PARALLEL_TOOL_CALLS` | parallel_tool_calls |
| `INCLUDE_REASONING` | include_reasoning |
| `REASONING` | reasoning |
| `REASONING_EFFORT` | reasoning_effort |
| `WEB_SEARCH_OPTIONS` | web_search_options |
| `VERBOSITY` | verbosity |
-11
View File
@@ -1,11 +0,0 @@
# Partition
Partitioning strategy for sorting: "model" (default) groups endpoints by model before sorting (fallback models remain fallbacks), "none" sorts all endpoints together regardless of model.
## Values
| Name | Value |
| ------- | ------- |
| `MODEL` | model |
| `NONE` | none |
@@ -1,12 +0,0 @@
# PayloadTooLargeResponseErrorData
Error data for PayloadTooLargeResponse
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `code` | *int* | :heavy_check_mark: | N/A |
| `message` | *str* | :heavy_check_mark: | N/A |
| `metadata` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
@@ -1,12 +0,0 @@
# PaymentRequiredResponseErrorData
Error data for PaymentRequiredResponse
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `code` | *int* | :heavy_check_mark: | N/A |
| `message` | *str* | :heavy_check_mark: | N/A |
| `metadata` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
-19
View File
@@ -1,19 +0,0 @@
# PDFParserEngine
The engine to use for parsing PDF files. "pdf-text" is deprecated and automatically redirected to "cloudflare-ai".
## Supported Types
### `components.PDFParserEngineEnum`
```python
value: components.PDFParserEngineEnum = /* values here */
```
### `components.PDFParserEnginePDFText`
```python
value: components.PDFParserEnginePDFText = /* values here */
```
-10
View File
@@ -1,10 +0,0 @@
# PDFParserOptions
Options for PDF parsing.
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ |
| `engine` | [Optional[components.PDFParserEngine]](../components/pdfparserengine.md) | :heavy_minus_sign: | The engine to use for parsing PDF files. "pdf-text" is deprecated and automatically redirected to "cloudflare-ai". | cloudflare-ai |
@@ -1,13 +0,0 @@
# PercentileLatencyCutoffs
Percentile-based latency cutoffs. All specified cutoffs must be met for an endpoint to be preferred.
## Fields
| Field | Type | Required | Description |
| ----------------------------- | ----------------------------- | ----------------------------- | ----------------------------- |
| `p50` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum p50 latency (seconds) |
| `p75` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum p75 latency (seconds) |
| `p90` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum p90 latency (seconds) |
| `p99` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum p99 latency (seconds) |
-13
View File
@@ -1,13 +0,0 @@
# PercentileStats
Latency percentiles in milliseconds over the last 30 minutes. Latency measures time to first token. Only visible when authenticated with an API key or cookie; returns null for unauthenticated requests.
## Fields
| Field | Type | Required | Description | Example |
| ------------------------ | ------------------------ | ------------------------ | ------------------------ | ------------------------ |
| `p50` | *float* | :heavy_check_mark: | Median (50th percentile) | 25.5 |
| `p75` | *float* | :heavy_check_mark: | 75th percentile | 35.2 |
| `p90` | *float* | :heavy_check_mark: | 90th percentile | 48.7 |
| `p99` | *float* | :heavy_check_mark: | 99th percentile | 85.3 |
@@ -1,13 +0,0 @@
# PercentileThroughputCutoffs
Percentile-based throughput cutoffs. All specified cutoffs must be met for an endpoint to be preferred.
## Fields
| Field | Type | Required | Description |
| ----------------------------------- | ----------------------------------- | ----------------------------------- | ----------------------------------- |
| `p50` | *OptionalNullable[float]* | :heavy_minus_sign: | Minimum p50 throughput (tokens/sec) |
| `p75` | *OptionalNullable[float]* | :heavy_minus_sign: | Minimum p75 throughput (tokens/sec) |
| `p90` | *OptionalNullable[float]* | :heavy_minus_sign: | Minimum p90 throughput (tokens/sec) |
| `p99` | *OptionalNullable[float]* | :heavy_minus_sign: | Minimum p99 throughput (tokens/sec) |
-11
View File
@@ -1,11 +0,0 @@
# PerRequestLimits
Per-request token limits
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------- | ------------------------------------- | ------------------------------------- | ------------------------------------- | ------------------------------------- |
| `completion_tokens` | *float* | :heavy_check_mark: | Maximum completion tokens per request | 1000 |
| `prompt_tokens` | *float* | :heavy_check_mark: | Maximum prompt tokens per request | 1000 |
-25
View File
@@ -1,25 +0,0 @@
# PreferredMaxLatency
Preferred maximum latency (in seconds). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints above the threshold(s) may still be used, but are deprioritized in routing. When using fallback models, this may cause a fallback model to be used instead of the primary model if it meets the threshold.
## Supported Types
### `float`
```python
value: float = /* values here */
```
### `components.PercentileLatencyCutoffs`
```python
value: components.PercentileLatencyCutoffs = /* values here */
```
### `Any`
```python
value: Any = /* values here */
```
-25
View File
@@ -1,25 +0,0 @@
# PreferredMinThroughput
Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below the threshold(s) may still be used, but are deprioritized in routing. When using fallback models, this may cause a fallback model to be used instead of the primary model if it meets the threshold.
## Supported Types
### `float`
```python
value: float = /* values here */
```
### `components.PercentileThroughputCutoffs`
```python
value: components.PercentileThroughputCutoffs = /* values here */
```
### `Any`
```python
value: Any = /* values here */
```
-22
View File
@@ -1,22 +0,0 @@
# Pricing
## Fields
| 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 |
-97
View File
@@ -1,97 +0,0 @@
# ProviderName
## Values
| Name | Value |
| ------------------- | ------------------- |
| `AKASH_ML` | AkashML |
| `AI21` | AI21 |
| `AION_LABS` | AionLabs |
| `ALIBABA` | Alibaba |
| `AMBIENT` | Ambient |
| `BAIDU` | Baidu |
| `AMAZON_BEDROCK` | Amazon Bedrock |
| `AMAZON_NOVA` | Amazon Nova |
| `ANTHROPIC` | Anthropic |
| `ARCEE_AI` | Arcee AI |
| `ATLAS_CLOUD` | AtlasCloud |
| `AVIAN` | Avian |
| `AZURE` | Azure |
| `BASE_TEN` | BaseTen |
| `BYTE_PLUS` | BytePlus |
| `BLACK_FOREST_LABS` | Black Forest Labs |
| `CEREBRAS` | Cerebras |
| `CHUTES` | Chutes |
| `CIRRASCALE` | Cirrascale |
| `CLARIFAI` | Clarifai |
| `CLOUDFLARE` | Cloudflare |
| `COHERE` | Cohere |
| `CRUCIBLE` | Crucible |
| `CRUSOE` | Crusoe |
| `DARKBLOOM` | Darkbloom |
| `DECART` | Decart |
| `DEEP_INFRA` | DeepInfra |
| `DEEP_SEEK` | DeepSeek |
| `DEKA_LLM` | DekaLLM |
| `DIGITAL_OCEAN` | DigitalOcean |
| `FEATHERLESS` | Featherless |
| `FIREWORKS` | Fireworks |
| `FRIENDLI` | Friendli |
| `GMI_CLOUD` | GMICloud |
| `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 |
| `MANCER_2` | Mancer 2 |
| `MINIMAX` | Minimax |
| `MODEL_RUN` | ModelRun |
| `MISTRAL` | Mistral |
| `MODULAR` | Modular |
| `MOONSHOT_AI` | Moonshot AI |
| `MORPH` | Morph |
| `N_COMPASS` | NCompass |
| `NEBIUS` | Nebius |
| `NEX_AGI` | Nex AGI |
| `NEXT_BIT` | NextBit |
| `NOVITA` | Novita |
| `NVIDIA` | Nvidia |
| `OPEN_AI` | OpenAI |
| `OPEN_INFERENCE` | OpenInference |
| `PARASAIL` | Parasail |
| `POOLSIDE` | Poolside |
| `PERCEPTRON` | Perceptron |
| `PERPLEXITY` | Perplexity |
| `PHALA` | Phala |
| `RECRAFT` | Recraft |
| `REKA` | Reka |
| `RELACE` | Relace |
| `SAKANA_AI` | Sakana AI |
| `SAMBA_NOVA` | SambaNova |
| `SEED` | Seed |
| `SILICON_FLOW` | SiliconFlow |
| `SOURCEFUL` | Sourceful |
| `STEP_FUN` | StepFun |
| `STEALTH` | Stealth |
| `STREAM_LAKE` | StreamLake |
| `SWITCHPOINT` | Switchpoint |
| `TENSTORRENT` | Tenstorrent |
| `TOGETHER` | Together |
| `UPSTAGE` | Upstage |
| `VENICE` | Venice |
| `WAFER` | Wafer |
| `WAND_B` | WandB |
| `XIAOMI` | Xiaomi |
| `X_AI` | xAI |
| `Z_AI` | Z.AI |
| `FAKE_PROVIDER` | FakeProvider |
@@ -1,12 +0,0 @@
# ProviderOverloadedResponseErrorData
Error data for ProviderOverloadedResponse
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `code` | *int* | :heavy_check_mark: | N/A |
| `message` | *str* | :heavy_check_mark: | N/A |
| `metadata` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
-22
View File
@@ -1,22 +0,0 @@
# ProviderPreferences
When multiple model providers are available, optionally indicate your routing preference.
## Fields
| Field | Type | Required | Description | Example |
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `allow_fallbacks` | *OptionalNullable[bool]* | :heavy_minus_sign: | Whether to allow backup providers to serve requests<br/>- true: (default) when the primary provider (or your custom providers in "order") is unavailable, use the next best provider.<br/>- false: use only the primary/custom provider, and return the upstream error if it's unavailable.<br/> | |
| `data_collection` | [OptionalNullable[components.DataCollection]](../components/datacollection.md) | :heavy_minus_sign: | Data collection setting. If no available model provider meets the requirement, your request will return an error.<br/>- allow: (default) allow providers which store user data non-transiently and may train on it<br/><br/>- deny: use only providers which do not collect user data. | allow |
| `enforce_distillable_text` | *OptionalNullable[bool]* | :heavy_minus_sign: | Whether to restrict routing to only models that allow text distillation. When true, only models where the author has allowed distillation will be used. | true |
| `ignore` | List[[components.Ignore](../components/ignore.md)] | :heavy_minus_sign: | List of provider slugs to ignore. If provided, this list is merged with your account-wide ignored provider settings for this request. | [<br/>"openai",<br/>"anthropic"<br/>] |
| `max_price` | [Optional[components.MaxPrice]](../components/maxprice.md) | :heavy_minus_sign: | The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion. | |
| `only` | List[[components.Only](../components/only.md)] | :heavy_minus_sign: | List of provider slugs to allow. If provided, this list is merged with your account-wide allowed provider settings for this request. | [<br/>"openai",<br/>"anthropic"<br/>] |
| `order` | List[[components.Order](../components/order.md)] | :heavy_minus_sign: | An ordered list of provider slugs. The router will attempt to use the first provider in the subset of this list that supports your requested model, and fall back to the next if it is unavailable. If no providers are available, the request will fail with an error message. | [<br/>"openai",<br/>"anthropic"<br/>] |
| `preferred_max_latency` | [OptionalNullable[components.PreferredMaxLatency]](../components/preferredmaxlatency.md) | :heavy_minus_sign: | Preferred maximum latency (in seconds). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints above the threshold(s) may still be used, but are deprioritized in routing. When using fallback models, this may cause a fallback model to be used instead of the primary model if it meets the threshold. | 5 |
| `preferred_min_throughput` | [OptionalNullable[components.PreferredMinThroughput]](../components/preferredminthroughput.md) | :heavy_minus_sign: | Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below the threshold(s) may still be used, but are deprioritized in routing. When using fallback models, this may cause a fallback model to be used instead of the primary model if it meets the threshold. | 100 |
| `quantizations` | List[[components.Quantization](../components/quantization.md)] | :heavy_minus_sign: | A list of quantization levels to filter the provider by. | |
| `require_parameters` | *OptionalNullable[bool]* | :heavy_minus_sign: | Whether to filter providers to only those that support the parameters you've provided. If this setting is omitted or set to false, then providers will receive only the parameters they support, and ignore the rest. | |
| `sort` | [OptionalNullable[components.Sort]](../components/sort.md) | :heavy_minus_sign: | The sorting strategy to use for this request, if "order" is not specified. When set, no load balancing is performed. | price |
| `zdr` | *OptionalNullable[bool]* | :heavy_minus_sign: | Whether to restrict routing to only ZDR (Zero Data Retention) endpoints. When true, only endpoints that do not retain prompts will be used. | true |
-13
View File
@@ -1,13 +0,0 @@
# ProviderSort
The provider sorting strategy (price, throughput, latency)
## Values
| Name | Value |
| ------------ | ------------ |
| `PRICE` | price |
| `THROUGHPUT` | throughput |
| `LATENCY` | latency |
| `EXACTO` | exacto |
-11
View File
@@ -1,11 +0,0 @@
# ProviderSortConfig
The provider sorting strategy (price, throughput, latency)
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `by` | [OptionalNullable[components.By]](../components/by.md) | :heavy_minus_sign: | The provider sorting strategy (price, throughput, latency) | price |
| `partition` | [OptionalNullable[components.Partition]](../components/partition.md) | :heavy_minus_sign: | Partitioning strategy for sorting: "model" (default) groups endpoints by model before sorting (fallback models remain fallbacks), "none" sorts all endpoints together regardless of model. | model |
-27
View File
@@ -1,27 +0,0 @@
# PublicEndpoint
Information about a specific model endpoint
## Fields
| Field | Type | Required | Description | Example |
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `context_length` | *int* | :heavy_check_mark: | N/A | |
| `latency_last_30m` | [Nullable[components.PercentileStats]](../components/percentilestats.md) | :heavy_check_mark: | Latency percentiles in milliseconds over the last 30 minutes. Latency measures time to first token. Only visible when authenticated with an API key or cookie; returns null for unauthenticated requests. | {<br/>"p50": 25.5,<br/>"p75": 35.2,<br/>"p90": 48.7,<br/>"p99": 85.3<br/>} |
| `max_completion_tokens` | *Nullable[int]* | :heavy_check_mark: | N/A | |
| `max_prompt_tokens` | *Nullable[int]* | :heavy_check_mark: | N/A | |
| `model_id` | *str* | :heavy_check_mark: | The unique identifier for the model (permaslug) | openai/gpt-4 |
| `model_name` | *str* | :heavy_check_mark: | N/A | |
| `name` | *str* | :heavy_check_mark: | N/A | |
| `pricing` | [components.Pricing](../components/pricing.md) | :heavy_check_mark: | N/A | |
| `provider_name` | [components.ProviderName](../components/providername.md) | :heavy_check_mark: | N/A | OpenAI |
| `quantization` | [Nullable[components.PublicEndpointQuantization]](../components/publicendpointquantization.md) | :heavy_check_mark: | N/A | fp16 |
| `status` | [Optional[components.EndpointStatus]](../components/endpointstatus.md) | :heavy_minus_sign: | N/A | 0 |
| `supported_parameters` | List[[components.Parameter](../components/parameter.md)] | :heavy_check_mark: | N/A | |
| `supports_implicit_caching` | *bool* | :heavy_check_mark: | N/A | |
| `tag` | *str* | :heavy_check_mark: | N/A | |
| `throughput_last_30m` | [Nullable[components.PercentileStats]](../components/percentilestats.md) | :heavy_check_mark: | N/A | {<br/>"p50": 25.5,<br/>"p75": 35.2,<br/>"p90": 48.7,<br/>"p99": 85.3<br/>} |
| `uptime_last_1d` | *Nullable[float]* | :heavy_check_mark: | Uptime percentage over the last 1 day, calculated as successful requests / (successful + error requests) * 100. Rate-limited requests are excluded. Returns null if insufficient data. | |
| `uptime_last_30m` | *Nullable[float]* | :heavy_check_mark: | N/A | |
| `uptime_last_5m` | *Nullable[float]* | :heavy_check_mark: | Uptime percentage over the last 5 minutes, calculated as successful requests / (successful + error requests) * 100. Rate-limited requests are excluded. Returns null if insufficient data. | |
@@ -1,16 +0,0 @@
# PublicEndpointQuantization
## Values
| Name | Value |
| --------- | --------- |
| `INT4` | int4 |
| `INT8` | int8 |
| `FP4` | fp4 |
| `FP6` | fp6 |
| `FP8` | fp8 |
| `FP16` | fp16 |
| `BF16` | bf16 |
| `FP32` | fp32 |
| `UNKNOWN` | unknown |
-24
View File
@@ -1,24 +0,0 @@
# PublicPricing
Pricing information for the model
## Fields
| 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 |
-9
View File
@@ -1,9 +0,0 @@
# Reason
## Values
| Name | Value |
| ------------------- | ------------------- |
| `MAX_OUTPUT_TOKENS` | max_output_tokens |
| `CONTENT_FILTER` | content_filter |
@@ -1,14 +0,0 @@
# ReasoningDetailEncrypted
Reasoning detail encrypted schema
## Fields
| Field | Type | Required | Description | Example |
| ---------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
| `data` | *str* | :heavy_check_mark: | N/A | |
| `format_` | [OptionalNullable[components.ReasoningFormat]](../components/reasoningformat.md) | :heavy_minus_sign: | N/A | unknown |
| `id` | *OptionalNullable[str]* | :heavy_minus_sign: | N/A | |
| `index` | *Optional[int]* | :heavy_minus_sign: | N/A | |
| `type` | [components.ReasoningDetailEncryptedType](../components/reasoningdetailencryptedtype.md) | :heavy_check_mark: | N/A | |
-14
View File
@@ -1,14 +0,0 @@
# ReasoningDetailSummary
Reasoning detail summary schema
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------ |
| `format_` | [OptionalNullable[components.ReasoningFormat]](../components/reasoningformat.md) | :heavy_minus_sign: | N/A | unknown |
| `id` | *OptionalNullable[str]* | :heavy_minus_sign: | N/A | |
| `index` | *Optional[int]* | :heavy_minus_sign: | N/A | |
| `summary` | *str* | :heavy_check_mark: | N/A | |
| `type` | [components.ReasoningDetailSummaryType](../components/reasoningdetailsummarytype.md) | :heavy_check_mark: | N/A | |

Some files were not shown because too many files have changed in this diff Show More