wassname/openrouter-python-sdk-retry-errors
1
0
Fork 0
mirror of https://github.com/wassname/openrouter-python-sdk-retry-errors.git synced 2026-09-12 12:40:42 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: regenerate Python SDK with updated OpenAPI spec

Browse Source 
Updates include:
- Updated OpenAPI spec with new component schemas
- Restructured component documentation with nested parameter types
- Added new components for plugin and provider configurations
- Updated chat generation params and response request structures
- Version bump and dependency updates
This commit is contained in:
Matt Apperson
2025-12-12 15:13:12 -05:00
parent 67ef52b03e
commit 61e5216764
65 changed files with 2256 additions and 494 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.speakeasy/in.openapi.yaml
+345 -12
View File
@@ -1054,6 +1054,7 @@ components:
type: string
nullable: true
enum:
- xhigh
- high
- medium
- low
@@ -3479,6 +3480,7 @@ components:
- Infermatic
- Inflection
- Liquid
- Mara
- Mancer 2
- Minimax
- ModelRun
@@ -3507,6 +3509,7 @@ components:
- Together
- Venice
- WandB
- Xiaomi
- xAI
- Z.AI
- FakeProvider
@@ -3536,12 +3539,8 @@ components:
performed.
example: price
BigNumberUnion:
anyOf:
- type: number
- type: string
- type: number
example: 1000
description: A value in string or number format that is a large number
type: string
description: A value in string format that is a large number
example: 1000
OpenResponsesRequest:
type: object
@@ -3736,10 +3735,23 @@ components:
$ref: '#/components/schemas/BigNumberUnion'
request:
$ref: '#/components/schemas/BigNumberUnion'
additionalProperties: false
description: >-
The object specifying the maximum price you want to pay for this request. USD price per million tokens,
for prompt and completion.
min_throughput:
type: number
nullable: true
example: 100
description: >-
The minimum throughput (in tokens per second) required for this request. Only providers serving the
model with at least this throughput will be used.
max_latency:
type: number
nullable: true
example: 5
description: >-
The maximum latency (in seconds) allowed for this request. Only providers serving the model with better
than this latency will be used.
additionalProperties: false
description: When multiple model providers are available, optionally indicate your routing preference.
plugins:
@@ -3760,6 +3772,9 @@ components:
type: string
enum:
- web
enabled:
type: boolean
description: Set to false to disable the web-search plugin for this request. Defaults to true.
max_results:
type: number
search_prompt:
@@ -3777,6 +3792,9 @@ components:
type: string
enum:
- file-parser
enabled:
type: boolean
description: Set to false to disable the file-parser plugin for this request. Defaults to true.
max_files:
type: number
pdf:
@@ -3796,9 +3814,21 @@ components:
type: string
enum:
- response-healing
enabled:
type: boolean
description: Set to false to disable the response-healing plugin for this request. Defaults to true.
required:
- id
description: Plugins you want to enable for this request, including their settings.
route:
type: string
nullable: true
enum:
- fallback
- sort
description: >-
Routing strategy for multiple models: "fallback" (default) uses secondary models as backups, "sort" sorts
all endpoints together by routing criteria.
user:
type: string
maxLength: 128
@@ -4594,6 +4624,87 @@ components:
uptime_last_30m: 99.5
supports_implicit_caching: true
__schema0:
type: array
items:
anyOf:
- type: string
enum:
- AI21
- AionLabs
- Alibaba
- Amazon Bedrock
- Amazon Nova
- Anthropic
- Arcee AI
- AtlasCloud
- Avian
- Azure
- BaseTen
- BytePlus
- Black Forest Labs
- Cerebras
- Chutes
- Cirrascale
- Clarifai
- Cloudflare
- Cohere
- Crusoe
- DeepInfra
- DeepSeek
- Featherless
- Fireworks
- Friendli
- GMICloud
- GoPomelo
- Google
- Google AI Studio
- Groq
- Hyperbolic
- Inception
- InferenceNet
- Infermatic
- Inflection
- Liquid
- Mara
- Mancer 2
- Minimax
- ModelRun
- Mistral
- Modular
- Moonshot AI
- Morph
- NCompass
- Nebius
- NextBit
- Novita
- Nvidia
- OpenAI
- OpenInference
- Parasail
- Perplexity
- Phala
- Relace
- SambaNova
- SiliconFlow
- Sourceful
- Stealth
- StreamLake
- Switchpoint
- Targon
- Together
- Venice
- WandB
- Xiaomi
- xAI
- Z.AI
- FakeProvider
- type: string
__schema1:
anyOf:
- type: number
- type: string
- type: number
__schema2:
anyOf:
- $ref: '#/components/schemas/ChatCompletionFinishReason'
- type: 'null'
@@ -5051,6 +5162,214 @@ components:
ChatGenerationParams:
type: object
properties:
provider:
description: When multiple model providers are available, optionally indicate your routing preference.
anyOf:
- type: object
properties:
allow_fallbacks:
description: >
Whether to allow backup providers to serve requests
- true: (default) when the primary provider (or your custom providers in "order") is unavailable,
use the next best provider.
- false: use only the primary/custom provider, and return the upstream error if it's unavailable.
anyOf:
- type: boolean
- type: 'null'
require_parameters:
description: >-
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.
anyOf:
- type: boolean
- type: 'null'
data_collection:
description: >-
Data collection setting. If no available model provider meets the requirement, your request will
return an error.
- allow: (default) allow providers which store user data non-transiently and may train on it
- deny: use only providers which do not collect user data.
anyOf:
- type: string
enum:
- deny
- allow
- type: 'null'
zdr:
anyOf:
- type: boolean
- type: 'null'
enforce_distillable_text:
anyOf:
- type: boolean
- type: 'null'
order:
description: >-
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.
anyOf:
- $ref: '#/components/schemas/__schema0'
- type: 'null'
only:
description: >-
List of provider slugs to allow. If provided, this list is merged with your account-wide allowed
provider settings for this request.
anyOf:
- $ref: '#/components/schemas/__schema0'
- type: 'null'
ignore:
description: >-
List of provider slugs to ignore. If provided, this list is merged with your account-wide ignored
provider settings for this request.
anyOf:
- $ref: '#/components/schemas/__schema0'
- type: 'null'
quantizations:
description: A list of quantization levels to filter the provider by.
anyOf:
- type: array
items:
type: string
enum:
- int4
- int8
- fp4
- fp6
- fp8
- fp16
- bf16
- fp32
- unknown
- type: 'null'
sort:
description: >-
The sorting strategy to use for this request, if "order" is not specified. When set, no load
balancing is performed.
anyOf:
- type: string
enum:
- price
- throughput
- latency
- type: 'null'
max_price:
description: >-
The object specifying the maximum price you want to pay for this request. USD price per million
tokens, for prompt and completion.
type: object
properties:
prompt:
$ref: '#/components/schemas/__schema1'
completion:
$ref: '#/components/schemas/__schema1'
image:
$ref: '#/components/schemas/__schema1'
audio:
$ref: '#/components/schemas/__schema1'
request:
$ref: '#/components/schemas/__schema1'
min_throughput:
description: >-
The minimum throughput (in tokens per second) required for this request. Only providers serving the
model with at least this throughput will be used.
anyOf:
- type: number
- type: 'null'
max_latency:
description: >-
The maximum latency (in seconds) allowed for this request. Only providers serving the model with
better than this latency will be used.
anyOf:
- type: number
- type: 'null'
additionalProperties: false
- type: 'null'
plugins:
description: Plugins you want to enable for this request, including their settings.
type: array
items:
oneOf:
- type: object
properties:
id:
type: string
const: moderation
required:
- id
- type: object
properties:
id:
type: string
const: web
enabled:
type: boolean
max_results:
type: number
search_prompt:
type: string
engine:
type: string
enum:
- native
- exa
required:
- id
- type: object
properties:
id:
type: string
const: file-parser
enabled:
type: boolean
max_files:
type: number
pdf:
type: object
properties:
engine:
type: string
enum:
- mistral-ocr
- pdf-text
- native
required:
- id
- type: object
properties:
id:
type: string
const: response-healing
enabled:
type: boolean
required:
- id
type: object
route:
description: >-
Routing strategy for multiple models: "fallback" (default) uses secondary models as backups, "sort" sorts
all endpoints together by routing criteria.
anyOf:
- type: string
enum:
- fallback
- sort
- type: 'null'
user:
type: string
session_id:
description: >-
A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for
observability. If provided in both the request body and the x-session-id header, the body value takes
precedence. Maximum of 128 characters.
type: string
maxLength: 128
messages:
minItems: 1
type: array
@@ -5120,6 +5439,7 @@ components:
- low
- medium
- high
- xhigh
- type: 'null'
summary:
anyOf:
@@ -5193,8 +5513,6 @@ components:
minimum: 0
maximum: 1
- type: 'null'
user:
type: string
debug:
type: object
properties:
@@ -5206,7 +5524,7 @@ components:
type: object
properties:
finish_reason:
$ref: '#/components/schemas/__schema0'
$ref: '#/components/schemas/__schema2'
index:
type: number
message:
@@ -5267,7 +5585,7 @@ components:
delta:
$ref: '#/components/schemas/ChatStreamingMessageChunk'
finish_reason:
$ref: '#/components/schemas/__schema0'
$ref: '#/components/schemas/__schema2'
index:
type: number
logprobs:
@@ -6173,10 +6491,23 @@ paths:
$ref: '#/components/schemas/BigNumberUnion'
request:
$ref: '#/components/schemas/BigNumberUnion'
additionalProperties: false
description: >-
The object specifying the maximum price you want to pay for this request. USD price per million
tokens, for prompt and completion.
min_throughput:
type: number
nullable: true
example: 100
description: >-
The minimum throughput (in tokens per second) required for this request. Only providers serving
the model with at least this throughput will be used.
max_latency:
type: number
nullable: true
example: 5
description: >-
The maximum latency (in seconds) allowed for this request. Only providers serving the model with
better than this latency will be used.
input_type:
type: string
required:
@@ -6816,6 +7147,7 @@ paths:
- Infermatic
- Inflection
- Liquid
- Mara
- Mancer 2
- Minimax
- ModelRun
@@ -6844,6 +7176,7 @@ paths:
- Together
- Venice
- WandB
- Xiaomi
- xAI
- Z.AI
- FakeProvider