> ## Documentation Index > Fetch the complete documentation index at: https://openrouter.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Update a private endpoint > Change any of the endpoint fields you own in one call; only the fields present change, and the response is the whole endpoint. `pricing` and `declared_parameters` replace their stored value, `settings` changes only the fields it names (`null` clears a limit or restores the provider default); routing picks these up for subsequent requests on drafts and active endpoints alike. `declared_zdr` and `declared_region` change on drafts and active endpoints alike; on an active endpoint the change keeps its validation and tested parameters, and routing applies it to subsequent requests. `upstream_model_id` and `base_url` re-point a draft: an omitted `upstream_model_id` or `base_url` keeps the stored one, omitted data-policy declarations are kept while the upstream is unchanged and cleared when it changes, and any change to the upstream or declarations of a draft clears earlier validation. Naming `upstream_model_id` or `base_url` on an active endpoint returns 409 `already_active` and writes nothing, even alongside other fields; delete and re-create instead. Every group is checked before anything is written: 400 `parameters_invalid` when `tool_choice` is declared without `tools` tested or declared, 400 `settings_invalid` when `max_prompt_tokens` exceeds the context length, both completion APIs are off, or `excluded_parameters` names a tested parameter, 422 `pricing_invalid` for rates the provider strategy cannot represent, or `pricing_cache_read_unsupported` or `pricing_cache_write_unsupported` when that rate is a cache rate the strategy has no SKU for. [Management key](/docs/guides/overview/auth/management-api-keys) required. ## OpenAPI ````yaml /openapi/openapi.yaml patch /private-endpoints/{id} openapi: 3.1.0 info: contact: email: support@openrouter.ai name: OpenRouter Support url: https://openrouter.ai/docs description: OpenAI-compatible API with additional OpenRouter features license: name: MIT url: https://opensource.org/licenses/MIT title: OpenRouter API version: 1.0.0 servers: - description: Production server url: https://openrouter.ai/api/v1 x-speakeasy-server-id: production security: - apiKey: [] tags: - description: API key management endpoints name: API Keys - description: Analytics and usage endpoints name: Analytics - description: Anthropic Messages endpoints name: Anthropic Messages - description: BYOK endpoints name: BYOK - description: >- Submit, list, poll, and delete asynchronous batches of inference requests. See https://openrouter.ai/docs/batch-quickstart. name: Batch - description: Benchmarks endpoints name: Benchmarks - description: Chat completion endpoints name: Chat - description: Task classification market-share endpoints name: Classifications - description: Containers endpoints name: Containers - description: Credit management endpoints name: Credits - description: >- Public OpenRouter usage datasets. Data returned by these endpoints is licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/): reuse and republish it, including commercially, with attribution to OpenRouter. name: Datasets - description: Text embedding endpoints name: Embeddings - description: Endpoint information name: Endpoints - description: External Users endpoints name: External Users - description: Files endpoints name: Files - description: Generation history endpoints name: Generations - description: Guardrail Policies endpoints name: Guardrail Policies - description: Guardrails endpoints name: Guardrails - description: Images endpoints name: Images - description: Model information endpoints name: Models - description: OAuth authentication endpoints name: OAuth - description: Observability endpoints name: Observability - description: Organization endpoints name: Organization - description: Presets endpoints name: Presets - description: Private Endpoints endpoints name: Private Endpoints - description: Private Providers endpoints name: Private Providers - description: Provider information endpoints name: Providers - description: Rerank endpoints name: Rerank - description: OpenAI-compatible Responses API endpoints name: Responses - description: >- Management endpoints for SCIM group-to-workspace mappings, authenticated with a management key. These are not the SCIM 2.0 connector endpoints for your identity provider. In your identity provider, enter the SCIM endpoint URL shown when you enable provisioning under Settings > Members > SCIM Mappings. See https://openrouter.ai/docs/guides/features/scim-mappings#set-up-provisioning. name: SCIM - description: Speech-to-text endpoints name: STT x-displayName: Transcriptions - description: >- System One endpoints for models such as Jev, compatible with the TypeSafe SDKs. See https://openrouter.ai/docs/guides/community/typesafe-sdk. name: SystemOne x-displayName: System One - description: Text-to-speech endpoints name: TTS x-displayName: Speech - description: >- The catalog of server tools OpenRouter runs on behalf of a model: accepted `tools[].type` spellings per API format, engines and pricing, and which endpoints run each tool natively. See https://openrouter.ai/docs/guides/features/server-tools. name: Tools - description: >- Store host-bound secrets for a workspace or for one intern. Scope is selected by the API key. Responses return metadata only, never secret values. See https://openrouter.ai/docs/guides/ori/vault. name: Vault - description: Video Generation endpoints name: Video Generation - description: Workspaces endpoints name: Workspaces - description: Alpha feature endpoints for Decisions requests name: alpha.decisions - description: Alpha feature endpoints for Extractions requests name: alpha.extractions externalDocs: description: OpenRouter Documentation url: https://openrouter.ai/docs paths: /private-endpoints/{id}: patch: tags: - Private Endpoints summary: Update a private endpoint description: >- Change any of the endpoint fields you own in one call; only the fields present change, and the response is the whole endpoint. `pricing` and `declared_parameters` replace their stored value, `settings` changes only the fields it names (`null` clears a limit or restores the provider default); routing picks these up for subsequent requests on drafts and active endpoints alike. `declared_zdr` and `declared_region` change on drafts and active endpoints alike; on an active endpoint the change keeps its validation and tested parameters, and routing applies it to subsequent requests. `upstream_model_id` and `base_url` re-point a draft: an omitted `upstream_model_id` or `base_url` keeps the stored one, omitted data-policy declarations are kept while the upstream is unchanged and cleared when it changes, and any change to the upstream or declarations of a draft clears earlier validation. Naming `upstream_model_id` or `base_url` on an active endpoint returns 409 `already_active` and writes nothing, even alongside other fields; delete and re-create instead. Every group is checked before anything is written: 400 `parameters_invalid` when `tool_choice` is declared without `tools` tested or declared, 400 `settings_invalid` when `max_prompt_tokens` exceeds the context length, both completion APIs are off, or `excluded_parameters` names a tested parameter, 422 `pricing_invalid` for rates the provider strategy cannot represent, or `pricing_cache_read_unsupported` or `pricing_cache_write_unsupported` when that rate is a cache rate the strategy has no SKU for. [Management key](/docs/guides/overview/auth/management-api-keys) required. operationId: updatePrivateEndpoint parameters: - description: Stable identifier of the private endpoint. in: path name: id required: true schema: description: Stable identifier of the private endpoint. example: 5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11 format: uuid type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/UpdatePrivateEndpointRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/PrivateEndpointResponse' description: The updated endpoint '400': content: application/json: example: error: code: 400 message: Invalid request parameters schema: $ref: '#/components/schemas/BadRequestResponse' description: Bad Request - Invalid request parameters or malformed input '401': content: application/json: example: error: code: 401 message: Missing Authentication header schema: $ref: '#/components/schemas/UnauthorizedResponse' description: Unauthorized - Authentication required or invalid credentials '403': content: application/json: example: error: code: 403 message: Only management keys can perform this operation schema: $ref: '#/components/schemas/ForbiddenResponse' description: Forbidden - Authentication successful but insufficient permissions '404': content: application/json: example: error: code: 404 message: Resource not found schema: $ref: '#/components/schemas/NotFoundResponse' description: Not Found - Resource does not exist '408': content: application/json: example: error: code: 408 message: Operation timed out. Please try again later. schema: $ref: '#/components/schemas/RequestTimeoutResponse' description: Request Timeout - Operation exceeded time limit '409': content: application/json: example: error: code: 409 message: Resource conflict. Please try again later. schema: $ref: '#/components/schemas/ConflictResponse' description: Conflict - Resource conflict or concurrent modification '422': content: application/json: example: error: code: 422 message: Invalid argument schema: $ref: '#/components/schemas/UnprocessableEntityResponse' description: Unprocessable Entity - Semantic validation failure '500': content: application/json: example: error: code: 500 message: Internal Server Error schema: $ref: '#/components/schemas/InternalServerResponse' description: Internal Server Error - Unexpected server error '502': content: application/json: example: error: code: 502 message: Provider returned error schema: $ref: '#/components/schemas/BadGatewayResponse' description: Bad Gateway - Provider/upstream API failure components: schemas: UpdatePrivateEndpointRequest: description: >- Only the fields present change. `base_url` and `upstream_model_id` are accepted on a draft only; `declared_zdr` and `declared_region` on drafts and active endpoints; `pricing` and `declared_parameters` replace their value; `settings` is itself a partial update where `null` clears a limit or restores the provider default. example: declared_parameters: - seed settings: context_length: 128000 properties: base_url: description: >- HTTPS base URL of your deployment. Required unless the provider derives its URL from the BYOK credential (Azure, Amazon Bedrock, Google Vertex). example: https://contoso.openai.azure.com minLength: 1 type: string declared_parameters: description: >- Parameters the upstream supports beyond the tested ones. Replaces the earlier declaration; tested parameters stay. Order and repeated names are ignored, but the list holds at most as many entries as there are declarable parameters, repeats included. `tool_choice` requires `tools` to be tested or declared. example: - temperature - seed items: $ref: '#/components/schemas/PrivateEndpointDeclaredParameter' maxItems: 25 type: array declared_region: description: Attest where this deployment processes data. enum: - global - europe - us - null example: us type: - string - 'null' declared_zdr: description: Attest that this deployment retains no prompt or completion data. type: - boolean - 'null' pricing: allOf: - $ref: '#/components/schemas/PrivateEndpointPricing' - description: >- Replaces the whole pricing object: omitting `cache_read` or `cache_write` reverts that rate to the pricing strategy default. settings: allOf: - $ref: '#/components/schemas/UpdatePrivateEndpointSettingsRequest' - description: >- Only the fields present change; an omitted field keeps its stored value and `null` clears a limit or reverts a flag to the provider default. upstream_model_id: description: Model or deployment identifier sent to the upstream provider. example: gpt-4o-prod minLength: 1 type: string type: object PrivateEndpointResponse: properties: data: $ref: '#/components/schemas/PrivateEndpoint' required: - data type: object BadRequestResponse: description: Bad Request - Invalid request parameters or malformed input example: error: code: 400 message: Invalid request parameters properties: error: $ref: '#/components/schemas/BadRequestResponseErrorData' openrouter_metadata: additionalProperties: {} type: - object - 'null' user_id: type: - string - 'null' required: - error type: object UnauthorizedResponse: description: Unauthorized - Authentication required or invalid credentials example: error: code: 401 message: Missing Authentication header properties: error: $ref: '#/components/schemas/UnauthorizedResponseErrorData' openrouter_metadata: additionalProperties: {} type: - object - 'null' user_id: type: - string - 'null' required: - error type: object ForbiddenResponse: description: Forbidden - Authentication successful but insufficient permissions example: error: code: 403 message: Only management keys can perform this operation properties: error: $ref: '#/components/schemas/ForbiddenResponseErrorData' openrouter_metadata: additionalProperties: {} type: - object - 'null' user_id: type: - string - 'null' required: - error type: object NotFoundResponse: description: Not Found - Resource does not exist example: error: code: 404 message: Resource not found properties: error: $ref: '#/components/schemas/NotFoundResponseErrorData' openrouter_metadata: additionalProperties: {} type: - object - 'null' user_id: type: - string - 'null' required: - error type: object RequestTimeoutResponse: description: Request Timeout - Operation exceeded time limit example: error: code: 408 message: Operation timed out. Please try again later. properties: error: $ref: '#/components/schemas/RequestTimeoutResponseErrorData' openrouter_metadata: additionalProperties: {} type: - object - 'null' user_id: type: - string - 'null' required: - error type: object ConflictResponse: description: Conflict - Resource conflict or concurrent modification example: error: code: 409 message: Resource conflict. Please try again later. properties: error: $ref: '#/components/schemas/ConflictResponseErrorData' openrouter_metadata: additionalProperties: {} type: - object - 'null' user_id: type: - string - 'null' required: - error type: object UnprocessableEntityResponse: description: Unprocessable Entity - Semantic validation failure example: error: code: 422 message: Invalid argument properties: error: $ref: '#/components/schemas/UnprocessableEntityResponseErrorData' openrouter_metadata: additionalProperties: {} type: - object - 'null' user_id: type: - string - 'null' required: - error type: object InternalServerResponse: description: Internal Server Error - Unexpected server error example: error: code: 500 message: Internal Server Error properties: error: $ref: '#/components/schemas/InternalServerResponseErrorData' openrouter_metadata: additionalProperties: {} type: - object - 'null' user_id: type: - string - 'null' required: - error type: object BadGatewayResponse: description: Bad Gateway - Provider/upstream API failure example: error: code: 502 message: Provider returned error properties: error: $ref: '#/components/schemas/BadGatewayResponseErrorData' openrouter_metadata: additionalProperties: {} type: - object - 'null' user_id: type: - string - 'null' required: - error type: object PrivateEndpointDeclaredParameter: description: A chat request parameter the endpoint accepts. enum: - temperature - top_p - top_k - min_p - top_a - frequency_penalty - presence_penalty - repetition_penalty - max_tokens - max_completion_tokens - logit_bias - logprobs - top_logprobs - prediction - seed - response_format - structured_outputs - stop - tools - tool_choice - parallel_tool_calls - reasoning - reasoning_effort - web_search_options - verbosity example: seed type: string PrivateEndpointPricing: description: >- Negotiated per-token rates reported for requests routed to this endpoint. example: cache_read: '0.00000025' cache_write: '0.000003125' completion: '0.00001' prompt: '0.0000025' properties: cache_read: description: >- USD per cache-read prompt token, as a decimal string. When omitted, inherited from the public endpoint of the same model and provider: scaled by its cache-read to prompt ratio, or left at the pricing strategy default when it publishes no cache-read rate. Required when there is no such endpoint and the provider bills cache reads. example: '0.00000025' pattern: ^\d+(\.\d+)?$ type: string cache_write: description: >- USD per cache-write prompt token, as a decimal string. When omitted, inherited from the public endpoint of the same model and provider: scaled by its cache-write to prompt ratio, or left at the pricing strategy default when it publishes no cache-write rate. Required when there is no such endpoint and the provider bills cache writes. example: '0.000003125' pattern: ^\d+(\.\d+)?$ type: string completion: description: USD per completion token, as a decimal string. example: '0.00001' pattern: ^\d+(\.\d+)?$ type: string prompt: description: USD per prompt token, as a decimal string. example: '0.0000025' pattern: ^\d+(\.\d+)?$ type: string required: - prompt - completion type: object UpdatePrivateEndpointSettingsRequest: description: >- Capabilities and limits to set over the ones copied from the public endpoint for this model and provider (or from the model). Omitted fields keep the copied values. example: context_length: 128000 reasoning: supported: true properties: completions: properties: chat: description: Serves `/chat/completions`; `null` uses the provider default. type: - boolean - 'null' text: description: Serves `/completions`; `null` uses the provider default. type: - boolean - 'null' type: object context_length: description: >- Longest prompt plus completion, in tokens, or `null` to keep the model default. example: 128000 minimum: 1 type: - integer - 'null' excluded_parameters: description: >- Request parameters the upstream rejects even though the model supports them; requests using one do not route here. Cannot name a tested parameter. example: - logit_bias items: enum: - temperature - top_p - top_k - min_p - top_a - frequency_penalty - presence_penalty - repetition_penalty - max_tokens - max_completion_tokens - logit_bias - logprobs - top_logprobs - prediction - seed - response_format - structured_outputs - stop - tools - tool_choice - parallel_tool_calls - include_reasoning - reasoning - reasoning_effort - web_search_options - verbosity type: string type: array inputs: properties: audio: description: Accepts audio input. `null` keeps the provider default. type: - boolean - 'null' base64_files: description: Accepts base64 file data. `null` keeps the provider default. type: - boolean - 'null' base64_images: description: Accepts base64 image data. `null` keeps the provider default. type: - boolean - 'null' file_urls: description: Accepts file URLs. `null` keeps the provider default. type: - boolean - 'null' image_urls: description: Accepts image URLs. `null` keeps the provider default. type: - boolean - 'null' type: object max_completion_tokens: description: >- Longest completion the upstream returns, in tokens, or `null` to keep the model default. example: 16384 minimum: 1 type: - integer - 'null' max_prompt_tokens: description: >- Longest prompt, in tokens, or `null` for no cap below the context length. Cannot exceed `context_length`, or the model context length while `context_length` is `null`. example: null minimum: 1 type: - integer - 'null' quantization: $ref: '#/components/schemas/PrivateEndpointQuantization' reasoning: properties: return_mechanism: $ref: '#/components/schemas/PrivateEndpointReasoningReturnMechanism' supported: description: Whether requests with `reasoning` route to this endpoint. example: true type: boolean type: object tool_choice: properties: auto: description: 'Accepts `tool_choice: "auto"`.' type: boolean function: description: Accepts a named function in `tool_choice`. type: boolean none: description: 'Accepts `tool_choice: "none"`.' type: boolean required: description: 'Accepts `tool_choice: "required"`.' type: boolean type: object type: object PrivateEndpoint: example: base_url: https://contoso.openai.azure.com declared_parameters: - temperature - seed declared_region: us declared_zdr: true id: 5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11 max_completion_tokens: 131072 model_name: 'OpenAI: GPT-4o' model_permaslug: openai/gpt-4o-2024-08-06 model_slug: openai/gpt-4o pricing: cache_read: '0.00000025' cache_write: '0.000003125' completion: '0.00001' prompt: '0.0000025' provider_name: Azure provider_slug: azure settings: completions: chat: true text: false context_length: 128000 excluded_parameters: - logit_bias inputs: audio: false base64_files: null base64_images: true file_urls: null image_urls: true max_completion_tokens: 16384 max_prompt_tokens: null quantization: bf16 reasoning: return_mechanism: reasoning supported: true tool_choice: auto: true function: false none: true required: true status: active tested_parameters: - tools - tool_choice - response_format upstream_model_id: gpt-4o-prod properties: base_url: description: >- HTTPS base URL of your deployment, or `null` for providers whose URL is derived from the BYOK credential (Azure, Amazon Bedrock, Google Vertex). example: https://contoso.openai.azure.com type: - string - 'null' declared_parameters: description: >- Parameters you declared the upstream supports. Requests that use a parameter only route to this endpoint when it is tested or declared. example: - temperature - seed items: type: string type: array declared_region: $ref: '#/components/schemas/PrivateEndpointDeclaredRegion' declared_zdr: description: >- Whether you attest this deployment retains no prompt or completion data. `null` means undeclared. example: true type: - boolean - 'null' id: description: Stable identifier of the private endpoint. example: 5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11 format: uuid type: string max_completion_tokens: description: >- Most completion tokens a request routed to this endpoint can produce, or `null` when the endpoint sets no cap beyond the model context length. example: 131072 type: - integer - 'null' model_name: description: >- Display name of the model, or `null` when the model is no longer listed. example: 'OpenAI: GPT-4o' type: - string - 'null' model_permaslug: description: Permanent slug of the model this endpoint serves. example: openai/gpt-4o-2024-08-06 type: string model_slug: description: Public model slug, or `null` when the model is no longer listed. example: openai/gpt-4o type: - string - 'null' pricing: $ref: '#/components/schemas/PrivateEndpointPricing' provider_name: description: Display name of the upstream provider. example: Azure type: string provider_slug: description: >- Slug of the upstream provider, or `null` when the provider is no longer listed. example: azure type: - string - 'null' settings: $ref: '#/components/schemas/PrivateEndpointSettings' status: $ref: '#/components/schemas/PrivateEndpointStatus' tested_parameters: description: >- Parameters a validation run proved the upstream honors (`tools`, `tool_choice`, `response_format`, `structured_outputs`, `stop`). Read-only; cleared when the upstream configuration changes. example: - tools - tool_choice - response_format items: type: string type: array upstream_model_id: description: Model or deployment identifier sent to the upstream provider. example: gpt-4o-prod type: string required: - id - status - model_permaslug - model_slug - model_name - provider_name - provider_slug - base_url - upstream_model_id - declared_zdr - declared_region - pricing - tested_parameters - declared_parameters - settings type: object BadRequestResponseErrorData: description: Error data for BadRequestResponse example: code: 400 message: Invalid request parameters properties: code: type: integer message: type: string metadata: additionalProperties: {} type: - object - 'null' required: - code - message type: object UnauthorizedResponseErrorData: description: Error data for UnauthorizedResponse example: code: 401 message: Missing Authentication header properties: code: type: integer message: type: string metadata: additionalProperties: {} type: - object - 'null' required: - code - message type: object ForbiddenResponseErrorData: description: Error data for ForbiddenResponse example: code: 403 message: Only management keys can perform this operation properties: code: type: integer message: type: string metadata: additionalProperties: {} type: - object - 'null' required: - code - message type: object NotFoundResponseErrorData: description: Error data for NotFoundResponse example: code: 404 message: Resource not found properties: code: type: integer message: type: string metadata: additionalProperties: {} type: - object - 'null' required: - code - message type: object RequestTimeoutResponseErrorData: description: Error data for RequestTimeoutResponse example: code: 408 message: Operation timed out. Please try again later. properties: code: type: integer message: type: string metadata: additionalProperties: {} type: - object - 'null' required: - code - message type: object ConflictResponseErrorData: description: Error data for ConflictResponse example: code: 409 message: Resource conflict. Please try again later. properties: code: type: integer message: type: string metadata: additionalProperties: {} type: - object - 'null' required: - code - message type: object UnprocessableEntityResponseErrorData: description: Error data for UnprocessableEntityResponse example: code: 422 message: Invalid argument properties: code: type: integer message: type: string metadata: additionalProperties: {} type: - object - 'null' required: - code - message type: object InternalServerResponseErrorData: description: Error data for InternalServerResponse example: code: 500 message: Internal Server Error properties: code: type: integer message: type: string metadata: additionalProperties: {} type: - object - 'null' required: - code - message type: object BadGatewayResponseErrorData: description: Error data for BadGatewayResponse example: code: 502 message: Provider returned error properties: code: type: integer message: type: string metadata: additionalProperties: {} type: - object - 'null' required: - code - message type: object PrivateEndpointQuantization: description: Weight precision the deployment runs at; `unknown` when not stated. enum: - int4 - int8 - fp4 - mxfp4 - nvfp4 - fp6 - fp8 - mxfp8 - fp16 - bf16 - fp32 - unknown example: bf16 type: string PrivateEndpointReasoningReturnMechanism: description: >- Where the upstream puts reasoning tokens in its response: `reasoning` and `reasoning-content` are response fields, `content-string` is inline in the message, `none` returns no reasoning. `null` uses the provider default. enum: - content-string - reasoning-content - reasoning - none - null example: reasoning type: - string - 'null' PrivateEndpointDeclaredRegion: description: >- Where you attest this deployment processes data. `global` means not regional; `null` means undeclared. enum: - global - europe - us - null example: us type: - string - 'null' PrivateEndpointSettings: description: >- Capabilities and limits routing uses for this endpoint. A new endpoint copies them from the public endpoint for the same model and provider, or from the model, and the owner can change them. Rate limits are not part of this object: a private endpoint is billed to its own upstream key, so request limits stay with the provider. example: completions: chat: true text: false context_length: 128000 excluded_parameters: - logit_bias inputs: audio: false base64_files: null base64_images: true file_urls: null image_urls: true max_completion_tokens: 16384 max_prompt_tokens: null quantization: bf16 reasoning: return_mechanism: reasoning supported: true tool_choice: auto: true function: false none: true required: true properties: completions: properties: chat: description: Serves `/chat/completions`; `null` uses the provider default. type: - boolean - 'null' text: description: Serves `/completions`; `null` uses the provider default. type: - boolean - 'null' required: - chat - text type: object context_length: description: >- Longest prompt plus completion, in tokens, or `null` to keep the model default. example: 128000 minimum: 1 type: - integer - 'null' excluded_parameters: description: >- Request parameters the upstream rejects even though the model supports them; requests using one do not route here. Cannot name a tested parameter. example: - logit_bias items: enum: - temperature - top_p - top_k - min_p - top_a - frequency_penalty - presence_penalty - repetition_penalty - max_tokens - max_completion_tokens - logit_bias - logprobs - top_logprobs - prediction - seed - response_format - structured_outputs - stop - tools - tool_choice - parallel_tool_calls - include_reasoning - reasoning - reasoning_effort - web_search_options - verbosity type: string type: array inputs: properties: audio: description: Accepts audio input. `null` keeps the provider default. type: - boolean - 'null' base64_files: description: Accepts base64 file data. `null` keeps the provider default. type: - boolean - 'null' base64_images: description: Accepts base64 image data. `null` keeps the provider default. type: - boolean - 'null' file_urls: description: Accepts file URLs. `null` keeps the provider default. type: - boolean - 'null' image_urls: description: Accepts image URLs. `null` keeps the provider default. type: - boolean - 'null' required: - image_urls - base64_images - file_urls - base64_files - audio type: object max_completion_tokens: description: >- Longest completion the upstream returns, in tokens, or `null` to keep the model default. example: 16384 minimum: 1 type: - integer - 'null' max_prompt_tokens: description: >- Longest prompt, in tokens, or `null` for no cap below the context length. Cannot exceed `context_length`, or the model context length while `context_length` is `null`. example: null minimum: 1 type: - integer - 'null' quantization: $ref: '#/components/schemas/PrivateEndpointQuantization' reasoning: properties: return_mechanism: $ref: '#/components/schemas/PrivateEndpointReasoningReturnMechanism' supported: description: Whether requests with `reasoning` route to this endpoint. example: true type: boolean required: - supported - return_mechanism type: object tool_choice: properties: auto: description: 'Accepts `tool_choice: "auto"`.' type: boolean function: description: Accepts a named function in `tool_choice`. type: boolean none: description: 'Accepts `tool_choice: "none"`.' type: boolean required: description: 'Accepts `tool_choice: "required"`.' type: boolean required: - none - auto - required - function type: object required: - context_length - max_prompt_tokens - max_completion_tokens - quantization - reasoning - inputs - tool_choice - excluded_parameters - completions type: object PrivateEndpointStatus: description: >- Lifecycle state. `draft` endpoints are not routable until validated and activated; `disabled` endpoints are activated but temporarily not routable. enum: - draft - active - disabled example: active type: string securitySchemes: apiKey: description: API key as bearer token in Authorization header scheme: bearer type: http ````