diff --git a/.speakeasy/in.openapi.yaml b/.speakeasy/in.openapi.yaml index 0a88e05..07dc908 100644 --- a/.speakeasy/in.openapi.yaml +++ b/.speakeasy/in.openapi.yaml @@ -12202,6 +12202,15 @@ components: image: '0' prompt: '0.00003' request: '0' + reasoning: + default_effort: medium + default_enabled: true + mandatory: false + supported_efforts: + - high + - medium + - low + - minimal supported_parameters: - temperature - top_p @@ -12264,6 +12273,8 @@ components: $ref: '#/components/schemas/PerRequestLimits' pricing: $ref: '#/components/schemas/PublicPricing' + reasoning: + $ref: '#/components/schemas/ModelReasoning' supported_parameters: description: List of supported parameters for this model items: @@ -12426,6 +12437,47 @@ components: description: Model to use for completion example: openai/gpt-4 type: string + ModelReasoning: + description: Reasoning effort configuration. Omitted for non-reasoning models and dynamic router models. + example: + default_effort: medium + default_enabled: true + mandatory: false + supported_efforts: + - high + - medium + - low + - minimal + properties: + default_effort: + allOf: + - $ref: '#/components/schemas/ReasoningEffort' + - description: >- + Default reasoning effort when the client enables reasoning without specifying effort. Maps to + `reasoning.effort` in chat requests. When `"none"`, prefer omitting effort unless the user explicitly + disables reasoning. + default_enabled: + description: Default reasoning enabled state when the client does not set `reasoning.enabled`. + type: boolean + mandatory: + description: When true, reasoning cannot be disabled and effort "none" is rejected. + type: boolean + supported_efforts: + description: >- + Allowed reasoning effort values for this model, in descending effort order (highest first). Null means no + allowlist — all gateway effort values are accepted. + items: + $ref: '#/components/schemas/ReasoningEffort' + nullable: true + type: array + supports_max_tokens: + description: >- + Present and `true` when the model accepts `reasoning.max_tokens` in requests (Anthropic-style) instead of or + in addition to `reasoning.effort`. Omitted otherwise. + type: boolean + required: + - mandatory + type: object ModelResponse: description: Single model response example: @@ -28837,7 +28889,7 @@ paths: id: openai/gpt-4 knowledge_cutoff: null links: - details: /api/v1/models/openai/gpt-5.4/endpoints + details: /api/v1/models/openai/gpt-4/endpoints name: GPT-4 per_request_limits: null pricing: