mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-08-06 13:20:23 +08:00
Project import generated by Copybara.
GitOrigin-RevId: 849282a42d3b2948d0ca0f7fd1427c31af709bbd
This commit is contained in:
OpenRouter Team
+67
-23
@@ -1,12 +1,12 @@
|
||||
lockVersion: 2.0.0
|
||||
id: cfd52247-6a25-4c6d-bbce-fe6fce0cd69d
|
||||
management:
|
||||
docChecksum: 775966841832e95cb8d37401c576b4b6
|
||||
docChecksum: 772a7ec8092cfd6437e71806e7b19e28
|
||||
docVersion: 1.0.0
|
||||
speakeasyVersion: 1.666.0
|
||||
generationVersion: 2.768.0
|
||||
releaseVersion: 0.0.16
|
||||
configChecksum: cd00e781b0ef78cfcb3fe812f51e93ff
|
||||
releaseVersion: 0.0.17
|
||||
configChecksum: 50ef18bf69272fc09c257e3562e1b0df
|
||||
repoURL: https://github.com/OpenRouterTeam/python-sdk.git
|
||||
installationURL: https://github.com/OpenRouterTeam/python-sdk.git
|
||||
published: true
|
||||
@@ -29,6 +29,7 @@ features:
|
||||
globalServerURLs: 3.2.0
|
||||
globals: 3.0.0
|
||||
groups: 3.0.1
|
||||
ignores: 3.0.1
|
||||
methodArguments: 1.0.2
|
||||
methodSecurity: 3.0.1
|
||||
nameOverrides: 3.0.1
|
||||
@@ -59,21 +60,23 @@ generatedFiles:
|
||||
- docs/components/chaterrorerror.md
|
||||
- docs/components/chatgenerationparams.md
|
||||
- docs/components/chatgenerationparamsdatacollection.md
|
||||
- docs/components/chatgenerationparamsengine.md
|
||||
- docs/components/chatgenerationparamsimageconfig.md
|
||||
- docs/components/chatgenerationparamsmaxprice.md
|
||||
- docs/components/chatgenerationparamspdf.md
|
||||
- docs/components/chatgenerationparamspdfengine.md
|
||||
- docs/components/chatgenerationparamspluginautorouter.md
|
||||
- docs/components/chatgenerationparamspluginfileparser.md
|
||||
- docs/components/chatgenerationparamspluginmoderation.md
|
||||
- docs/components/chatgenerationparamspluginresponsehealing.md
|
||||
- docs/components/chatgenerationparamspluginunion.md
|
||||
- docs/components/chatgenerationparamspluginweb.md
|
||||
- docs/components/chatgenerationparamspreferredmaxlatency.md
|
||||
- docs/components/chatgenerationparamspreferredmaxlatencyunion.md
|
||||
- docs/components/chatgenerationparamspreferredminthroughput.md
|
||||
- docs/components/chatgenerationparamspreferredminthroughputunion.md
|
||||
- docs/components/chatgenerationparamsprovider.md
|
||||
- docs/components/chatgenerationparamsresponseformatjsonobject.md
|
||||
- docs/components/chatgenerationparamsresponseformatpython.md
|
||||
- docs/components/chatgenerationparamsresponseformattext.md
|
||||
- docs/components/chatgenerationparamsresponseformatunion.md
|
||||
- docs/components/chatgenerationparamsroute.md
|
||||
- docs/components/chatgenerationparamsstop.md
|
||||
- docs/components/chatgenerationtokenusage.md
|
||||
- docs/components/chatmessagecontentitem.md
|
||||
@@ -123,16 +126,17 @@ generatedFiles:
|
||||
- docs/components/edgenetworktimeoutresponseerrordata.md
|
||||
- docs/components/effort.md
|
||||
- docs/components/endpointstatus.md
|
||||
- docs/components/engine.md
|
||||
- docs/components/filecitation.md
|
||||
- docs/components/filecitationtype.md
|
||||
- docs/components/filepath.md
|
||||
- docs/components/filepathtype.md
|
||||
- docs/components/forbiddenresponseerrordata.md
|
||||
- docs/components/idautorouter.md
|
||||
- docs/components/idfileparser.md
|
||||
- docs/components/idmoderation.md
|
||||
- docs/components/idresponsehealing.md
|
||||
- docs/components/idweb.md
|
||||
- docs/components/ignore.md
|
||||
- docs/components/imagegenerationstatus.md
|
||||
- docs/components/imageurl.md
|
||||
- docs/components/inputmodality.md
|
||||
@@ -144,6 +148,7 @@ generatedFiles:
|
||||
- docs/components/message.md
|
||||
- docs/components/messagecontent.md
|
||||
- docs/components/messagedeveloper.md
|
||||
- docs/components/modality.md
|
||||
- docs/components/model.md
|
||||
- docs/components/modelarchitecture.md
|
||||
- docs/components/modelarchitectureinstructtype.md
|
||||
@@ -155,7 +160,6 @@ generatedFiles:
|
||||
- docs/components/namedtoolchoicefunction.md
|
||||
- docs/components/notfoundresponseerrordata.md
|
||||
- docs/components/object.md
|
||||
- docs/components/only.md
|
||||
- docs/components/openairesponsesannotation.md
|
||||
- docs/components/openairesponsesincludable.md
|
||||
- docs/components/openairesponsesincompletedetails.md
|
||||
@@ -254,17 +258,19 @@ generatedFiles:
|
||||
- docs/components/openresponsesreasoningsummarytextdoneeventtype.md
|
||||
- docs/components/openresponsesreasoningtype.md
|
||||
- docs/components/openresponsesrequest.md
|
||||
- docs/components/openresponsesrequestengine.md
|
||||
- docs/components/openresponsesrequestignore.md
|
||||
- docs/components/openresponsesrequestimageconfig.md
|
||||
- docs/components/openresponsesrequestmaxprice.md
|
||||
- docs/components/openresponsesrequestpdf.md
|
||||
- docs/components/openresponsesrequestpdfengine.md
|
||||
- docs/components/openresponsesrequestonly.md
|
||||
- docs/components/openresponsesrequestorder.md
|
||||
- docs/components/openresponsesrequestpluginautorouter.md
|
||||
- docs/components/openresponsesrequestpluginfileparser.md
|
||||
- docs/components/openresponsesrequestpluginmoderation.md
|
||||
- docs/components/openresponsesrequestpluginresponsehealing.md
|
||||
- docs/components/openresponsesrequestpluginunion.md
|
||||
- docs/components/openresponsesrequestpluginweb.md
|
||||
- docs/components/openresponsesrequestprovider.md
|
||||
- docs/components/openresponsesrequestroute.md
|
||||
- docs/components/openresponsesrequestsort.md
|
||||
- docs/components/openresponsesrequesttoolfunction.md
|
||||
- docs/components/openresponsesrequesttoolunion.md
|
||||
- docs/components/openresponsesrequesttype.md
|
||||
@@ -300,7 +306,6 @@ generatedFiles:
|
||||
- docs/components/openresponseswebsearchtool.md
|
||||
- docs/components/openresponseswebsearchtoolfilters.md
|
||||
- docs/components/openresponseswebsearchtooltype.md
|
||||
- docs/components/order.md
|
||||
- docs/components/outputitemimagegenerationcall.md
|
||||
- docs/components/outputitemimagegenerationcalltype.md
|
||||
- docs/components/outputmessage.md
|
||||
@@ -316,15 +321,38 @@ generatedFiles:
|
||||
- docs/components/parameter.md
|
||||
- docs/components/part1.md
|
||||
- docs/components/part2.md
|
||||
- docs/components/partition.md
|
||||
- docs/components/payloadtoolargeresponseerrordata.md
|
||||
- docs/components/paymentrequiredresponseerrordata.md
|
||||
- docs/components/pdf.md
|
||||
- docs/components/pdfengine.md
|
||||
- docs/components/pdfparserengine.md
|
||||
- docs/components/pdfparseroptions.md
|
||||
- docs/components/percentilelatencycutoffs.md
|
||||
- docs/components/percentilestats.md
|
||||
- docs/components/percentilethroughputcutoffs.md
|
||||
- docs/components/perrequestlimits.md
|
||||
- docs/components/preferredmaxlatency.md
|
||||
- docs/components/preferredminthroughput.md
|
||||
- docs/components/pricing.md
|
||||
- docs/components/prompt.md
|
||||
- docs/components/prompttokensdetails.md
|
||||
- docs/components/providername.md
|
||||
- docs/components/provideroverloadedresponseerrordata.md
|
||||
- docs/components/providerpreferences.md
|
||||
- docs/components/providerpreferencesignore.md
|
||||
- docs/components/providerpreferencesmaxprice.md
|
||||
- docs/components/providerpreferencesonly.md
|
||||
- docs/components/providerpreferencesorder.md
|
||||
- docs/components/providerpreferencespartition.md
|
||||
- docs/components/providerpreferencesprovidersort.md
|
||||
- docs/components/providerpreferencesprovidersortconfig.md
|
||||
- docs/components/providerpreferencessortunion.md
|
||||
- docs/components/providersort.md
|
||||
- docs/components/providersortconfig.md
|
||||
- docs/components/providersortconfigenum.md
|
||||
- docs/components/providersortconfigunion.md
|
||||
- docs/components/providersortunion.md
|
||||
- docs/components/publicendpoint.md
|
||||
- docs/components/publicendpointquantization.md
|
||||
- docs/components/publicpricing.md
|
||||
@@ -373,6 +401,7 @@ generatedFiles:
|
||||
- docs/components/responsesoutputitemfunctioncallstatusunion.md
|
||||
- docs/components/responsesoutputitemfunctioncalltype.md
|
||||
- docs/components/responsesoutputitemreasoning.md
|
||||
- docs/components/responsesoutputitemreasoningformat.md
|
||||
- docs/components/responsesoutputitemreasoningstatuscompleted.md
|
||||
- docs/components/responsesoutputitemreasoningstatusincomplete.md
|
||||
- docs/components/responsesoutputitemreasoningstatusinprogress.md
|
||||
@@ -386,6 +415,7 @@ generatedFiles:
|
||||
- docs/components/responsesoutputmessagestatusinprogress.md
|
||||
- docs/components/responsesoutputmessagestatusunion.md
|
||||
- docs/components/responsesoutputmessagetype.md
|
||||
- docs/components/responsesoutputmodality.md
|
||||
- docs/components/responsessearchcontextsize.md
|
||||
- docs/components/responseswebsearchcalloutput.md
|
||||
- docs/components/responseswebsearchcalloutputtype.md
|
||||
@@ -393,12 +423,18 @@ generatedFiles:
|
||||
- docs/components/responseswebsearchuserlocationtype.md
|
||||
- docs/components/responsetextconfig.md
|
||||
- docs/components/responsetextconfigverbosity.md
|
||||
- docs/components/route.md
|
||||
- docs/components/schema0.md
|
||||
- docs/components/schema0enum.md
|
||||
- docs/components/schema3.md
|
||||
- docs/components/schema3reasoningencrypted.md
|
||||
- docs/components/schema3reasoningsummary.md
|
||||
- docs/components/schema3reasoningtext.md
|
||||
- docs/components/schema5.md
|
||||
- docs/components/security.md
|
||||
- docs/components/servicetier.md
|
||||
- docs/components/serviceunavailableresponseerrordata.md
|
||||
- docs/components/sort.md
|
||||
- docs/components/sortenum.md
|
||||
- docs/components/streamoptions.md
|
||||
- docs/components/systemmessage.md
|
||||
- docs/components/systemmessagecontent.md
|
||||
@@ -440,6 +476,7 @@ generatedFiles:
|
||||
- docs/components/variables.md
|
||||
- docs/components/videourl1.md
|
||||
- docs/components/videourl2.md
|
||||
- docs/components/websearchengine.md
|
||||
- docs/components/websearchpreviewtooluserlocation.md
|
||||
- docs/components/websearchpreviewtooluserlocationtype.md
|
||||
- docs/components/websearchstatus.md
|
||||
@@ -473,7 +510,6 @@ generatedFiles:
|
||||
- docs/operations/createcoinbasechargeresponse.md
|
||||
- docs/operations/createcoinbasechargesecurity.md
|
||||
- docs/operations/createembeddingsdata.md
|
||||
- docs/operations/createembeddingsprovider.md
|
||||
- docs/operations/createembeddingsrequest.md
|
||||
- docs/operations/createembeddingsresponse.md
|
||||
- docs/operations/createembeddingsresponsebody.md
|
||||
@@ -502,13 +538,11 @@ generatedFiles:
|
||||
- docs/operations/getkeyresponse.md
|
||||
- docs/operations/getmodelsrequest.md
|
||||
- docs/operations/getparametersdata.md
|
||||
- docs/operations/getparametersprovider.md
|
||||
- docs/operations/getparametersrequest.md
|
||||
- docs/operations/getparametersresponse.md
|
||||
- docs/operations/getparameterssecurity.md
|
||||
- docs/operations/getuseractivityrequest.md
|
||||
- docs/operations/getuseractivityresponse.md
|
||||
- docs/operations/ignore.md
|
||||
- docs/operations/imageurl.md
|
||||
- docs/operations/input.md
|
||||
- docs/operations/inputunion.md
|
||||
@@ -521,12 +555,9 @@ generatedFiles:
|
||||
- docs/operations/listprovidersresponse.md
|
||||
- docs/operations/listrequest.md
|
||||
- docs/operations/listresponse.md
|
||||
- docs/operations/maxprice.md
|
||||
- docs/operations/metadata.md
|
||||
- docs/operations/object.md
|
||||
- docs/operations/objectembedding.md
|
||||
- docs/operations/only.md
|
||||
- docs/operations/order.md
|
||||
- docs/operations/ratelimit.md
|
||||
- docs/operations/sendchatcompletionrequestresponse.md
|
||||
- docs/operations/supportedparameter.md
|
||||
@@ -570,6 +601,7 @@ generatedFiles:
|
||||
- src/openrouter/completions.py
|
||||
- src/openrouter/components/__init__.py
|
||||
- src/openrouter/components/_schema0.py
|
||||
- src/openrouter/components/_schema3.py
|
||||
- src/openrouter/components/activityitem.py
|
||||
- src/openrouter/components/assistantmessage.py
|
||||
- src/openrouter/components/badgatewayresponseerrordata.py
|
||||
@@ -667,10 +699,20 @@ generatedFiles:
|
||||
- src/openrouter/components/parameter.py
|
||||
- src/openrouter/components/payloadtoolargeresponseerrordata.py
|
||||
- src/openrouter/components/paymentrequiredresponseerrordata.py
|
||||
- src/openrouter/components/pdfparserengine.py
|
||||
- src/openrouter/components/pdfparseroptions.py
|
||||
- src/openrouter/components/percentilelatencycutoffs.py
|
||||
- src/openrouter/components/percentilestats.py
|
||||
- src/openrouter/components/percentilethroughputcutoffs.py
|
||||
- src/openrouter/components/perrequestlimits.py
|
||||
- src/openrouter/components/preferredmaxlatency.py
|
||||
- src/openrouter/components/preferredminthroughput.py
|
||||
- src/openrouter/components/providername.py
|
||||
- src/openrouter/components/provideroverloadedresponseerrordata.py
|
||||
- src/openrouter/components/providerpreferences.py
|
||||
- src/openrouter/components/providersort.py
|
||||
- src/openrouter/components/providersortconfig.py
|
||||
- src/openrouter/components/providersortunion.py
|
||||
- src/openrouter/components/publicendpoint.py
|
||||
- src/openrouter/components/publicpricing.py
|
||||
- src/openrouter/components/quantization.py
|
||||
@@ -696,6 +738,7 @@ generatedFiles:
|
||||
- src/openrouter/components/responsesoutputitemfunctioncall.py
|
||||
- src/openrouter/components/responsesoutputitemreasoning.py
|
||||
- src/openrouter/components/responsesoutputmessage.py
|
||||
- src/openrouter/components/responsesoutputmodality.py
|
||||
- src/openrouter/components/responsessearchcontextsize.py
|
||||
- src/openrouter/components/responseswebsearchcalloutput.py
|
||||
- src/openrouter/components/responseswebsearchuserlocation.py
|
||||
@@ -712,6 +755,7 @@ generatedFiles:
|
||||
- src/openrouter/components/unprocessableentityresponseerrordata.py
|
||||
- src/openrouter/components/urlcitation.py
|
||||
- src/openrouter/components/usermessage.py
|
||||
- src/openrouter/components/websearchengine.py
|
||||
- src/openrouter/components/websearchpreviewtooluserlocation.py
|
||||
- src/openrouter/components/websearchstatus.py
|
||||
- src/openrouter/credits.py
|
||||
@@ -961,7 +1005,7 @@ examples:
|
||||
slug: "<value>"
|
||||
responses:
|
||||
"200":
|
||||
application/json: {"data": {"id": "openai/gpt-4", "name": "GPT-4", "created": 1692901234, "description": "GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy.", "architecture": {"tokenizer": "GPT", "instruct_type": "chatml", "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"]}, "endpoints": [{"name": "OpenAI: GPT-4", "model_name": "GPT-4", "context_length": 8192, "pricing": {"prompt": "0.00003", "completion": "0.00006"}, "provider_name": "OpenAI", "tag": "openai", "quantization": "fp16", "max_completion_tokens": 4096, "max_prompt_tokens": 8192, "supported_parameters": ["temperature", "top_p", "max_tokens", "frequency_penalty", "presence_penalty"], "uptime_last_30m": 99.5, "supports_implicit_caching": true}]}}
|
||||
application/json: {"data": {"id": "openai/gpt-4", "name": "GPT-4", "created": 1692901234, "description": "GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy.", "architecture": {"tokenizer": "GPT", "instruct_type": "chatml", "modality": "text->text", "input_modalities": ["text"], "output_modalities": ["text"]}, "endpoints": [{"name": "OpenAI: GPT-4", "model_name": "GPT-4", "context_length": 8192, "pricing": {"prompt": "0.00003", "completion": "0.00006"}, "provider_name": "OpenAI", "tag": "openai", "quantization": "fp16", "max_completion_tokens": 4096, "max_prompt_tokens": 8192, "supported_parameters": ["temperature", "top_p", "max_tokens", "frequency_penalty", "presence_penalty"], "uptime_last_30m": 99.5, "supports_implicit_caching": true, "latency_last_30m": {"p50": 0.25, "p75": 0.35, "p90": 0.48, "p99": 0.85}, "throughput_last_30m": {"p50": 45.2, "p75": 38.5, "p90": 28.3, "p99": 15.1}}]}}
|
||||
"404":
|
||||
application/json: {"error": {"code": 404, "message": "Resource not found"}}
|
||||
"500":
|
||||
@@ -970,7 +1014,7 @@ examples:
|
||||
speakeasy-default-list-endpoints-zdr:
|
||||
responses:
|
||||
"200":
|
||||
application/json: {"data": [{"name": "OpenAI: GPT-4", "model_name": "GPT-4", "context_length": 8192, "pricing": {"prompt": "0.00003", "completion": "0.00006"}, "provider_name": "OpenAI", "tag": "openai", "quantization": "fp16", "max_completion_tokens": 4096, "max_prompt_tokens": 8192, "supported_parameters": ["temperature", "top_p", "max_tokens"], "uptime_last_30m": 99.5, "supports_implicit_caching": true}]}
|
||||
application/json: {"data": [{"name": "OpenAI: GPT-4", "model_name": "GPT-4", "context_length": 8192, "pricing": {"prompt": "0.00003", "completion": "0.00006"}, "provider_name": "OpenAI", "tag": "openai", "quantization": "fp16", "max_completion_tokens": 4096, "max_prompt_tokens": 8192, "supported_parameters": ["temperature", "top_p", "max_tokens"], "uptime_last_30m": 99.5, "supports_implicit_caching": true, "latency_last_30m": {"p50": 25.5, "p75": 35.2, "p90": 48.7, "p99": 85.3}, "throughput_last_30m": {"p50": 25.5, "p75": 35.2, "p90": 48.7, "p99": 85.3}}]}
|
||||
"500":
|
||||
application/json: {"error": {"code": 500, "message": "Internal Server Error"}}
|
||||
getParameters:
|
||||
|
||||
+3
-1
@@ -31,7 +31,7 @@ generation:
|
||||
skipResponseBodyAssertions: false
|
||||
preApplyUnionDiscriminators: true
|
||||
python:
|
||||
version: 0.0.16
|
||||
version: 0.0.17
|
||||
additionalDependencies:
|
||||
dev: {}
|
||||
main: {}
|
||||
@@ -39,6 +39,8 @@ python:
|
||||
- id
|
||||
- object
|
||||
- input
|
||||
- models
|
||||
- hash
|
||||
asyncMode: both
|
||||
authors:
|
||||
- OpenRouter
|
||||
|
||||
+527
-236
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,10 @@
|
||||
lintVersion: 1.0.0
|
||||
defaultRuleset: openrouter
|
||||
rulesets:
|
||||
openrouter:
|
||||
rulesets:
|
||||
- speakeasy-recommended
|
||||
- speakeasy-generation
|
||||
rules:
|
||||
oas3-missing-example:
|
||||
severity: "off"
|
||||
+507
-221
@@ -269,7 +269,25 @@ components:
|
||||
allOf:
|
||||
- $ref: '#/components/schemas/OutputItemReasoning'
|
||||
- type: object
|
||||
properties: {}
|
||||
properties:
|
||||
signature:
|
||||
type: string
|
||||
nullable: true
|
||||
description: A signature for the reasoning content, used for verification
|
||||
example: EvcBCkgIChABGAIqQKkSDbRuVEQUk9qN1odC098l9SEj...
|
||||
format:
|
||||
type: string
|
||||
nullable: true
|
||||
enum:
|
||||
- unknown
|
||||
- openai-responses-v1
|
||||
- azure-openai-responses-v1
|
||||
- xai-responses-v1
|
||||
- anthropic-claude-v1
|
||||
- google-gemini-v1
|
||||
description: The format of the reasoning content
|
||||
example: anthropic-claude-v1
|
||||
x-speakeasy-unknown-values: allow
|
||||
example:
|
||||
id: reasoning-123
|
||||
type: reasoning
|
||||
@@ -280,6 +298,8 @@ components:
|
||||
content:
|
||||
- type: reasoning_text
|
||||
text: First, we analyze the problem...
|
||||
signature: EvcBCkgIChABGAIqQKkSDbRuVEQUk9qN1odC098l9SEj...
|
||||
format: anthropic-claude-v1
|
||||
description: An output item containing reasoning
|
||||
OutputItemFunctionCall:
|
||||
type: object
|
||||
@@ -3239,6 +3259,7 @@ components:
|
||||
enum:
|
||||
- unknown
|
||||
- openai-responses-v1
|
||||
- azure-openai-responses-v1
|
||||
- xai-responses-v1
|
||||
- anthropic-claude-v1
|
||||
- google-gemini-v1
|
||||
@@ -3434,6 +3455,12 @@ components:
|
||||
example:
|
||||
summary: auto
|
||||
enabled: true
|
||||
ResponsesOutputModality:
|
||||
type: string
|
||||
enum:
|
||||
- text
|
||||
- image
|
||||
x-speakeasy-unknown-values: allow
|
||||
OpenAIResponsesIncludable:
|
||||
type: string
|
||||
enum:
|
||||
@@ -3487,7 +3514,6 @@ components:
|
||||
- Fireworks
|
||||
- Friendli
|
||||
- GMICloud
|
||||
- GoPomelo
|
||||
- Google
|
||||
- Google AI Studio
|
||||
- Groq
|
||||
@@ -3517,13 +3543,14 @@ components:
|
||||
- Phala
|
||||
- Relace
|
||||
- SambaNova
|
||||
- Seed
|
||||
- SiliconFlow
|
||||
- Sourceful
|
||||
- Stealth
|
||||
- StreamLake
|
||||
- Switchpoint
|
||||
- Targon
|
||||
- Together
|
||||
- Upstage
|
||||
- Venice
|
||||
- WandB
|
||||
- Xiaomi
|
||||
@@ -3548,19 +3575,113 @@ components:
|
||||
x-speakeasy-unknown-values: allow
|
||||
ProviderSort:
|
||||
type: string
|
||||
nullable: true
|
||||
enum:
|
||||
- price
|
||||
- throughput
|
||||
- latency
|
||||
description: >-
|
||||
The sorting strategy to use for this request, if "order" is not specified. When set, no load balancing is performed.
|
||||
example: price
|
||||
x-speakeasy-unknown-values: allow
|
||||
ProviderSortConfig:
|
||||
type: object
|
||||
properties:
|
||||
by:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ProviderSort'
|
||||
- type: 'null'
|
||||
partition:
|
||||
anyOf:
|
||||
- type: string
|
||||
enum:
|
||||
- model
|
||||
- none
|
||||
x-speakeasy-unknown-values: allow
|
||||
- type: 'null'
|
||||
BigNumberUnion:
|
||||
type: string
|
||||
description: A value in string format that is a large number
|
||||
example: 1000
|
||||
PercentileThroughputCutoffs:
|
||||
type: object
|
||||
properties:
|
||||
p50:
|
||||
type: number
|
||||
nullable: true
|
||||
description: Minimum p50 throughput (tokens/sec)
|
||||
p75:
|
||||
type: number
|
||||
nullable: true
|
||||
description: Minimum p75 throughput (tokens/sec)
|
||||
p90:
|
||||
type: number
|
||||
nullable: true
|
||||
description: Minimum p90 throughput (tokens/sec)
|
||||
p99:
|
||||
type: number
|
||||
nullable: true
|
||||
description: Minimum p99 throughput (tokens/sec)
|
||||
description: Percentile-based throughput cutoffs. All specified cutoffs must be met for an endpoint to be preferred.
|
||||
example:
|
||||
p50: 100
|
||||
p90: 50
|
||||
PreferredMinThroughput:
|
||||
anyOf:
|
||||
- type: number
|
||||
- $ref: '#/components/schemas/PercentileThroughputCutoffs'
|
||||
- nullable: true
|
||||
description: >-
|
||||
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.
|
||||
example: 100
|
||||
PercentileLatencyCutoffs:
|
||||
type: object
|
||||
properties:
|
||||
p50:
|
||||
type: number
|
||||
nullable: true
|
||||
description: Maximum p50 latency (seconds)
|
||||
p75:
|
||||
type: number
|
||||
nullable: true
|
||||
description: Maximum p75 latency (seconds)
|
||||
p90:
|
||||
type: number
|
||||
nullable: true
|
||||
description: Maximum p90 latency (seconds)
|
||||
p99:
|
||||
type: number
|
||||
nullable: true
|
||||
description: Maximum p99 latency (seconds)
|
||||
description: Percentile-based latency cutoffs. All specified cutoffs must be met for an endpoint to be preferred.
|
||||
example:
|
||||
p50: 5
|
||||
p90: 10
|
||||
PreferredMaxLatency:
|
||||
anyOf:
|
||||
- type: number
|
||||
- $ref: '#/components/schemas/PercentileLatencyCutoffs'
|
||||
- nullable: true
|
||||
description: >-
|
||||
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.
|
||||
example: 5
|
||||
WebSearchEngine:
|
||||
type: string
|
||||
enum:
|
||||
- native
|
||||
- exa
|
||||
description: The search engine to use for web search.
|
||||
x-speakeasy-unknown-values: allow
|
||||
PDFParserEngine:
|
||||
type: string
|
||||
enum:
|
||||
- mistral-ocr
|
||||
- pdf-text
|
||||
- native
|
||||
description: The engine to use for parsing PDF files.
|
||||
x-speakeasy-unknown-values: allow
|
||||
PDFParserOptions:
|
||||
type: object
|
||||
properties:
|
||||
engine:
|
||||
$ref: '#/components/schemas/PDFParserEngine'
|
||||
description: Options for PDF parsing.
|
||||
OpenResponsesRequest:
|
||||
type: object
|
||||
properties:
|
||||
@@ -3631,6 +3752,24 @@ components:
|
||||
minimum: 0
|
||||
top_k:
|
||||
type: number
|
||||
image_config:
|
||||
type: object
|
||||
additionalProperties:
|
||||
anyOf:
|
||||
- type: string
|
||||
- type: number
|
||||
description: >-
|
||||
Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/features/multimodal/image-generation for more details.
|
||||
example:
|
||||
aspect_ratio: '16:9'
|
||||
modalities:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/ResponsesOutputModality'
|
||||
description: Output modalities for the response. Supported values are "text" and "image".
|
||||
example:
|
||||
- text
|
||||
- image
|
||||
prompt_cache_key:
|
||||
type: string
|
||||
nullable: true
|
||||
@@ -3733,7 +3872,13 @@ components:
|
||||
$ref: '#/components/schemas/Quantization'
|
||||
description: A list of quantization levels to filter the provider by.
|
||||
sort:
|
||||
$ref: '#/components/schemas/ProviderSort'
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ProviderSort'
|
||||
- $ref: '#/components/schemas/ProviderSortConfig'
|
||||
- nullable: true
|
||||
description: >-
|
||||
The sorting strategy to use for this request, if "order" is not specified. When set, no load balancing is performed.
|
||||
example: price
|
||||
max_price:
|
||||
type: object
|
||||
properties:
|
||||
@@ -3749,24 +3894,37 @@ components:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
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.
|
||||
preferred_min_throughput:
|
||||
$ref: '#/components/schemas/PreferredMinThroughput'
|
||||
preferred_max_latency:
|
||||
$ref: '#/components/schemas/PreferredMaxLatency'
|
||||
additionalProperties: false
|
||||
description: When multiple model providers are available, optionally indicate your routing preference.
|
||||
plugins:
|
||||
type: array
|
||||
items:
|
||||
oneOf:
|
||||
- type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
enum:
|
||||
- auto-router
|
||||
enabled:
|
||||
type: boolean
|
||||
description: Set to false to disable the auto-router plugin for this request. Defaults to true.
|
||||
allowed_models:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: >-
|
||||
List of model patterns to filter which models the auto-router can route between. Supports wildcards (e.g., "anthropic/*" matches all Anthropic models). When not specified, uses the default supported models list.
|
||||
example:
|
||||
- anthropic/*
|
||||
- openai/gpt-4o
|
||||
- google/*
|
||||
required:
|
||||
- id
|
||||
- type: object
|
||||
properties:
|
||||
id:
|
||||
@@ -3789,11 +3947,7 @@ components:
|
||||
search_prompt:
|
||||
type: string
|
||||
engine:
|
||||
type: string
|
||||
enum:
|
||||
- native
|
||||
- exa
|
||||
x-speakeasy-unknown-values: allow
|
||||
$ref: '#/components/schemas/WebSearchEngine'
|
||||
required:
|
||||
- id
|
||||
- type: object
|
||||
@@ -3806,15 +3960,7 @@ components:
|
||||
type: boolean
|
||||
description: Set to false to disable the file-parser plugin for this request. Defaults to true.
|
||||
pdf:
|
||||
type: object
|
||||
properties:
|
||||
engine:
|
||||
type: string
|
||||
enum:
|
||||
- mistral-ocr
|
||||
- pdf-text
|
||||
- native
|
||||
x-speakeasy-unknown-values: allow
|
||||
$ref: '#/components/schemas/PDFParserOptions'
|
||||
required:
|
||||
- id
|
||||
- type: object
|
||||
@@ -3835,8 +3981,12 @@ components:
|
||||
enum:
|
||||
- fallback
|
||||
- sort
|
||||
deprecated: true
|
||||
description: >-
|
||||
Routing strategy for multiple models: "fallback" (default) uses secondary models as backups, "sort" sorts all endpoints together by routing criteria.
|
||||
**DEPRECATED** Use providers.sort.partition instead. Backwards-compatible alias for providers.sort.partition. Accepts legacy values: "fallback" (maps to "model"), "sort" (maps to "none").
|
||||
x-speakeasy-deprecation-message: Use providers.sort.partition instead.
|
||||
x-speakeasy-ignore: true
|
||||
x-fern-ignore: true
|
||||
x-speakeasy-unknown-values: allow
|
||||
user:
|
||||
type: string
|
||||
@@ -3994,6 +4144,100 @@ components:
|
||||
amount: 100
|
||||
sender: '0x1234567890123456789012345678901234567890'
|
||||
chain_id: 1
|
||||
ProviderPreferences:
|
||||
type: object
|
||||
properties:
|
||||
allow_fallbacks:
|
||||
type: boolean
|
||||
nullable: true
|
||||
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.
|
||||
|
||||
require_parameters:
|
||||
type: boolean
|
||||
nullable: true
|
||||
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.
|
||||
data_collection:
|
||||
$ref: '#/components/schemas/DataCollection'
|
||||
zdr:
|
||||
type: boolean
|
||||
nullable: true
|
||||
description: >-
|
||||
Whether to restrict routing to only ZDR (Zero Data Retention) endpoints. When true, only endpoints that do not retain prompts will be used.
|
||||
example: true
|
||||
enforce_distillable_text:
|
||||
type: boolean
|
||||
nullable: true
|
||||
description: >-
|
||||
Whether to restrict routing to only models that allow text distillation. When true, only models where the author has allowed distillation will be used.
|
||||
example: true
|
||||
order:
|
||||
type: array
|
||||
nullable: true
|
||||
items:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ProviderName'
|
||||
- type: string
|
||||
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.
|
||||
only:
|
||||
type: array
|
||||
nullable: true
|
||||
items:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ProviderName'
|
||||
- type: string
|
||||
description: >-
|
||||
List of provider slugs to allow. If provided, this list is merged with your account-wide allowed provider settings for this request.
|
||||
ignore:
|
||||
type: array
|
||||
nullable: true
|
||||
items:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ProviderName'
|
||||
- type: string
|
||||
description: >-
|
||||
List of provider slugs to ignore. If provided, this list is merged with your account-wide ignored provider settings for this request.
|
||||
quantizations:
|
||||
type: array
|
||||
nullable: true
|
||||
items:
|
||||
$ref: '#/components/schemas/Quantization'
|
||||
description: A list of quantization levels to filter the provider by.
|
||||
sort:
|
||||
allOf:
|
||||
- $ref: '#/components/schemas/ProviderSort'
|
||||
- anyOf:
|
||||
- $ref: '#/components/schemas/ProviderSort'
|
||||
- $ref: '#/components/schemas/ProviderSortConfig'
|
||||
- nullable: true
|
||||
description: >-
|
||||
The sorting strategy to use for this request, if "order" is not specified. When set, no load balancing is performed.
|
||||
max_price:
|
||||
type: object
|
||||
properties:
|
||||
prompt:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
completion:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
image:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
audio:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
request:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
description: >-
|
||||
The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion.
|
||||
preferred_min_throughput:
|
||||
$ref: '#/components/schemas/PreferredMinThroughput'
|
||||
preferred_max_latency:
|
||||
$ref: '#/components/schemas/PreferredMaxLatency'
|
||||
description: Provider routing preferences for the request.
|
||||
PublicPricing:
|
||||
type: object
|
||||
properties:
|
||||
@@ -4205,6 +4449,7 @@ components:
|
||||
- parallel_tool_calls
|
||||
- include_reasoning
|
||||
- reasoning
|
||||
- reasoning_effort
|
||||
- web_search_options
|
||||
- verbosity
|
||||
example: temperature
|
||||
@@ -4431,6 +4676,32 @@ components:
|
||||
- -10
|
||||
example: 0
|
||||
x-speakeasy-unknown-values: allow
|
||||
PercentileStats:
|
||||
type: object
|
||||
nullable: true
|
||||
properties:
|
||||
p50:
|
||||
type: number
|
||||
description: Median (50th percentile)
|
||||
example: 25.5
|
||||
p75:
|
||||
type: number
|
||||
description: 75th percentile
|
||||
example: 35.2
|
||||
p90:
|
||||
type: number
|
||||
description: 90th percentile
|
||||
example: 48.7
|
||||
p99:
|
||||
type: number
|
||||
description: 99th percentile
|
||||
example: 85.3
|
||||
required:
|
||||
- p50
|
||||
- p75
|
||||
- p90
|
||||
- p99
|
||||
description: Latency percentiles in seconds over the last 30 minutes. Latency measures time to first token.
|
||||
PublicEndpoint:
|
||||
type: object
|
||||
properties:
|
||||
@@ -4498,6 +4769,13 @@ components:
|
||||
nullable: true
|
||||
supports_implicit_caching:
|
||||
type: boolean
|
||||
latency_last_30m:
|
||||
$ref: '#/components/schemas/PercentileStats'
|
||||
throughput_last_30m:
|
||||
allOf:
|
||||
- $ref: '#/components/schemas/PercentileStats'
|
||||
- description: >-
|
||||
Throughput percentiles in tokens per second over the last 30 minutes. Throughput measures output token generation speed.
|
||||
required:
|
||||
- name
|
||||
- model_name
|
||||
@@ -4511,6 +4789,8 @@ components:
|
||||
- supported_parameters
|
||||
- uptime_last_30m
|
||||
- supports_implicit_caching
|
||||
- latency_last_30m
|
||||
- throughput_last_30m
|
||||
description: Information about a specific model endpoint
|
||||
example:
|
||||
name: 'OpenAI: GPT-4'
|
||||
@@ -4533,6 +4813,16 @@ components:
|
||||
status: 0
|
||||
uptime_last_30m: 99.5
|
||||
supports_implicit_caching: true
|
||||
latency_last_30m:
|
||||
p50: 0.25
|
||||
p75: 0.35
|
||||
p90: 0.48
|
||||
p99: 0.85
|
||||
throughput_last_30m:
|
||||
p50: 45.2
|
||||
p75: 38.5
|
||||
p90: 28.3
|
||||
p99: 15.1
|
||||
ListEndpointsResponse:
|
||||
type: object
|
||||
properties:
|
||||
@@ -4636,6 +4926,16 @@ components:
|
||||
status: default
|
||||
uptime_last_30m: 99.5
|
||||
supports_implicit_caching: true
|
||||
latency_last_30m:
|
||||
p50: 0.25
|
||||
p75: 0.35
|
||||
p90: 0.48
|
||||
p99: 0.85
|
||||
throughput_last_30m:
|
||||
p50: 45.2
|
||||
p75: 38.5
|
||||
p90: 28.3
|
||||
p99: 15.1
|
||||
__schema0:
|
||||
type: array
|
||||
items:
|
||||
@@ -4668,7 +4968,6 @@ components:
|
||||
- Fireworks
|
||||
- Friendli
|
||||
- GMICloud
|
||||
- GoPomelo
|
||||
- Google
|
||||
- Google AI Studio
|
||||
- Groq
|
||||
@@ -4698,13 +4997,14 @@ components:
|
||||
- Phala
|
||||
- Relace
|
||||
- SambaNova
|
||||
- Seed
|
||||
- SiliconFlow
|
||||
- Sourceful
|
||||
- Stealth
|
||||
- StreamLake
|
||||
- Switchpoint
|
||||
- Targon
|
||||
- Together
|
||||
- Upstage
|
||||
- Venice
|
||||
- WandB
|
||||
- Xiaomi
|
||||
@@ -4722,6 +5022,80 @@ components:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ChatCompletionFinishReason'
|
||||
- type: 'null'
|
||||
__schema3:
|
||||
oneOf:
|
||||
- type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: reasoning.summary
|
||||
summary:
|
||||
type: string
|
||||
id:
|
||||
$ref: '#/components/schemas/__schema4'
|
||||
format:
|
||||
$ref: '#/components/schemas/__schema5'
|
||||
index:
|
||||
$ref: '#/components/schemas/__schema6'
|
||||
required:
|
||||
- type
|
||||
- summary
|
||||
- type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: reasoning.encrypted
|
||||
data:
|
||||
type: string
|
||||
id:
|
||||
$ref: '#/components/schemas/__schema4'
|
||||
format:
|
||||
$ref: '#/components/schemas/__schema5'
|
||||
index:
|
||||
$ref: '#/components/schemas/__schema6'
|
||||
required:
|
||||
- type
|
||||
- data
|
||||
- type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: reasoning.text
|
||||
text:
|
||||
anyOf:
|
||||
- type: string
|
||||
- type: 'null'
|
||||
signature:
|
||||
anyOf:
|
||||
- type: string
|
||||
- type: 'null'
|
||||
id:
|
||||
$ref: '#/components/schemas/__schema4'
|
||||
format:
|
||||
$ref: '#/components/schemas/__schema5'
|
||||
index:
|
||||
$ref: '#/components/schemas/__schema6'
|
||||
required:
|
||||
- type
|
||||
type: object
|
||||
__schema4:
|
||||
anyOf:
|
||||
- type: string
|
||||
- type: 'null'
|
||||
__schema5:
|
||||
anyOf:
|
||||
- type: string
|
||||
enum:
|
||||
- unknown
|
||||
- openai-responses-v1
|
||||
- azure-openai-responses-v1
|
||||
- xai-responses-v1
|
||||
- anthropic-claude-v1
|
||||
- google-gemini-v1
|
||||
x-speakeasy-unknown-values: allow
|
||||
- type: 'null'
|
||||
__schema6:
|
||||
type: number
|
||||
ModelName:
|
||||
type: string
|
||||
ChatMessageContentItemText:
|
||||
@@ -4940,6 +5314,8 @@ components:
|
||||
properties:
|
||||
cached_tokens:
|
||||
type: number
|
||||
cache_write_tokens:
|
||||
type: number
|
||||
audio_tokens:
|
||||
type: number
|
||||
video_tokens:
|
||||
@@ -5264,12 +5640,7 @@ components:
|
||||
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
|
||||
x-speakeasy-unknown-values: allow
|
||||
- $ref: '#/components/schemas/ProviderSortUnion'
|
||||
- type: 'null'
|
||||
max_price:
|
||||
description: >-
|
||||
@@ -5286,17 +5657,55 @@ components:
|
||||
$ref: '#/components/schemas/__schema1'
|
||||
request:
|
||||
$ref: '#/components/schemas/__schema1'
|
||||
min_throughput:
|
||||
preferred_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.
|
||||
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.
|
||||
anyOf:
|
||||
- type: number
|
||||
- anyOf:
|
||||
- type: number
|
||||
- type: object
|
||||
properties:
|
||||
p50:
|
||||
anyOf:
|
||||
- type: number
|
||||
- type: 'null'
|
||||
p75:
|
||||
anyOf:
|
||||
- type: number
|
||||
- type: 'null'
|
||||
p90:
|
||||
anyOf:
|
||||
- type: number
|
||||
- type: 'null'
|
||||
p99:
|
||||
anyOf:
|
||||
- type: number
|
||||
- type: 'null'
|
||||
- type: 'null'
|
||||
max_latency:
|
||||
preferred_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.
|
||||
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.
|
||||
anyOf:
|
||||
- type: number
|
||||
- anyOf:
|
||||
- type: number
|
||||
- type: object
|
||||
properties:
|
||||
p50:
|
||||
anyOf:
|
||||
- type: number
|
||||
- type: 'null'
|
||||
p75:
|
||||
anyOf:
|
||||
- type: number
|
||||
- type: 'null'
|
||||
p90:
|
||||
anyOf:
|
||||
- type: number
|
||||
- type: 'null'
|
||||
p99:
|
||||
anyOf:
|
||||
- type: number
|
||||
- type: 'null'
|
||||
- type: 'null'
|
||||
additionalProperties: false
|
||||
- type: 'null'
|
||||
@@ -5305,6 +5714,19 @@ components:
|
||||
type: array
|
||||
items:
|
||||
oneOf:
|
||||
- type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
const: auto-router
|
||||
enabled:
|
||||
type: boolean
|
||||
allowed_models:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
required:
|
||||
- id
|
||||
- type: object
|
||||
properties:
|
||||
id:
|
||||
@@ -5361,8 +5783,6 @@ components:
|
||||
- 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:
|
||||
@@ -5441,12 +5861,12 @@ components:
|
||||
anyOf:
|
||||
- type: string
|
||||
enum:
|
||||
- none
|
||||
- minimal
|
||||
- low
|
||||
- medium
|
||||
- high
|
||||
- xhigh
|
||||
- high
|
||||
- medium
|
||||
- low
|
||||
- minimal
|
||||
- none
|
||||
x-speakeasy-unknown-values: allow
|
||||
- type: 'null'
|
||||
summary:
|
||||
@@ -5526,8 +5946,28 @@ components:
|
||||
properties:
|
||||
echo_upstream_body:
|
||||
type: boolean
|
||||
image_config:
|
||||
type: object
|
||||
propertyNames:
|
||||
type: string
|
||||
additionalProperties:
|
||||
anyOf:
|
||||
- type: string
|
||||
- type: number
|
||||
modalities:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
enum:
|
||||
- text
|
||||
- image
|
||||
x-speakeasy-unknown-values: allow
|
||||
required:
|
||||
- messages
|
||||
ProviderSortUnion:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ProviderSort'
|
||||
- $ref: '#/components/schemas/ProviderSortConfig'
|
||||
ChatResponseChoice:
|
||||
type: object
|
||||
properties:
|
||||
@@ -5537,6 +5977,10 @@ components:
|
||||
type: number
|
||||
message:
|
||||
$ref: '#/components/schemas/AssistantMessage'
|
||||
reasoning_details:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/__schema3'
|
||||
logprobs:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ChatMessageTokenLogprobs'
|
||||
@@ -5587,6 +6031,10 @@ components:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/ChatStreamingMessageToolCall'
|
||||
reasoning_details:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/__schema3'
|
||||
ChatStreamingChoice:
|
||||
type: object
|
||||
properties:
|
||||
@@ -6413,99 +6861,7 @@ paths:
|
||||
user:
|
||||
type: string
|
||||
provider:
|
||||
type: object
|
||||
properties:
|
||||
allow_fallbacks:
|
||||
type: boolean
|
||||
nullable: true
|
||||
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.
|
||||
|
||||
require_parameters:
|
||||
type: boolean
|
||||
nullable: true
|
||||
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.
|
||||
data_collection:
|
||||
$ref: '#/components/schemas/DataCollection'
|
||||
zdr:
|
||||
type: boolean
|
||||
nullable: true
|
||||
description: >-
|
||||
Whether to restrict routing to only ZDR (Zero Data Retention) endpoints. When true, only endpoints that do not retain prompts will be used.
|
||||
example: true
|
||||
enforce_distillable_text:
|
||||
type: boolean
|
||||
nullable: true
|
||||
description: >-
|
||||
Whether to restrict routing to only models that allow text distillation. When true, only models where the author has allowed distillation will be used.
|
||||
example: true
|
||||
order:
|
||||
type: array
|
||||
nullable: true
|
||||
items:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ProviderName'
|
||||
- type: string
|
||||
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.
|
||||
only:
|
||||
type: array
|
||||
nullable: true
|
||||
items:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ProviderName'
|
||||
- type: string
|
||||
description: >-
|
||||
List of provider slugs to allow. If provided, this list is merged with your account-wide allowed provider settings for this request.
|
||||
ignore:
|
||||
type: array
|
||||
nullable: true
|
||||
items:
|
||||
anyOf:
|
||||
- $ref: '#/components/schemas/ProviderName'
|
||||
- type: string
|
||||
description: >-
|
||||
List of provider slugs to ignore. If provided, this list is merged with your account-wide ignored provider settings for this request.
|
||||
quantizations:
|
||||
type: array
|
||||
nullable: true
|
||||
items:
|
||||
$ref: '#/components/schemas/Quantization'
|
||||
description: A list of quantization levels to filter the provider by.
|
||||
sort:
|
||||
$ref: '#/components/schemas/ProviderSort'
|
||||
max_price:
|
||||
type: object
|
||||
properties:
|
||||
prompt:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
completion:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
image:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
audio:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
request:
|
||||
$ref: '#/components/schemas/BigNumberUnion'
|
||||
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.
|
||||
$ref: '#/components/schemas/ProviderPreferences'
|
||||
input_type:
|
||||
type: string
|
||||
required:
|
||||
@@ -7095,78 +7451,7 @@ paths:
|
||||
name: slug
|
||||
in: path
|
||||
- schema:
|
||||
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
|
||||
x-speakeasy-unknown-values: allow
|
||||
$ref: '#/components/schemas/ProviderName'
|
||||
required: false
|
||||
name: provider
|
||||
in: query
|
||||
@@ -7211,6 +7496,7 @@ paths:
|
||||
- parallel_tool_calls
|
||||
- include_reasoning
|
||||
- reasoning
|
||||
- reasoning_effort
|
||||
- web_search_options
|
||||
- verbosity
|
||||
x-speakeasy-unknown-values: allow
|
||||
|
||||
@@ -8,19 +8,20 @@ sources:
|
||||
- latest
|
||||
OpenRouter API:
|
||||
sourceNamespace: open-router-chat-completions-api
|
||||
sourceRevisionDigest: sha256:cfb565b0217763fa566062e31b6f01db05dfec6bdd0746b429f03b8600588989
|
||||
sourceBlobDigest: sha256:b985c3342982a1c6e2163e6bb1ebc6066117f1d4c3dfc6fa219768cf6f7fc8d1
|
||||
sourceRevisionDigest: sha256:fcc289022d99776aaf9434e14ccc3c9878a847384b300158c84391c9f4aed6ce
|
||||
sourceBlobDigest: sha256:40c2ad7a48417d63a674f078aa75768dc7266885f38003ab3e5c00067d444fbe
|
||||
tags:
|
||||
- latest
|
||||
- subtree-sync-import-python-sdk
|
||||
- 1.0.0
|
||||
targets:
|
||||
open-router:
|
||||
source: OpenRouter API
|
||||
sourceNamespace: open-router-chat-completions-api
|
||||
sourceRevisionDigest: sha256:cfb565b0217763fa566062e31b6f01db05dfec6bdd0746b429f03b8600588989
|
||||
sourceBlobDigest: sha256:b985c3342982a1c6e2163e6bb1ebc6066117f1d4c3dfc6fa219768cf6f7fc8d1
|
||||
sourceRevisionDigest: sha256:fcc289022d99776aaf9434e14ccc3c9878a847384b300158c84391c9f4aed6ce
|
||||
sourceBlobDigest: sha256:40c2ad7a48417d63a674f078aa75768dc7266885f38003ab3e5c00067d444fbe
|
||||
codeSamplesNamespace: open-router-python-code-samples
|
||||
codeSamplesRevisionDigest: sha256:badb3333f4862c5024a05b0b8456c4491edca4c2e3511c10da240942fc5e5397
|
||||
codeSamplesRevisionDigest: sha256:567674342c32a59ace54f464472abd2784897dbbe9e4bb6f953480ea84e03cf9
|
||||
workflow:
|
||||
workflowVersion: 1.0.0
|
||||
speakeasyVersion: 1.666.0
|
||||
|
||||
Reference in New Issue
Block a user