> ## Documentation Index > Fetch the complete documentation index at: https://docs.usehasp.com/llms.txt > Use this file to discover all available pages before exploring further. # Handle an OpenAI Chat Completions-compatible request, streaming or returning the assembled response ## OpenAPI ````yaml /openapi/v1.json post /chat/completions openapi: 3.1.0 info: title: HASP AI API version: '2026-07-12' description: >- The HASP Public AI API is the regulated-AI substrate for healthcare and other regulated industries — identity, policy, audit, compliance, and PHI handling for AI inference, exposed via two surfaces: - **Native (`/v1/ai/*`)**: HASP-native chat with full event taxonomy, run lifecycle, and PHI metadata. - **Anthropic-compat (`/v1/messages`)**: Drop-in replacement for `@anthropic-ai/sdk` — change only `baseURL`. All Gateway compliance checks (BAA, credits, PHI policy) apply. All requests require an API key (`Authorization: Bearer hasp_api_live_`). See [Authentication](https://docs.usehasp.com/ai-api/authentication) for key management. servers: - url: https://api.usehasp.com/v1 description: Production security: - http: [] paths: /chat/completions: post: tags: - ChatCompletions summary: >- Handle an OpenAI Chat Completions-compatible request, streaming or returning the assembled response operationId: v1.chat.completions requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionsRequest' responses: '200': description: '' content: application/json: schema: anyOf: - type: object properties: id: type: string object: type: string const: chat.completion created: type: integer model: {} choices: type: array prefixItems: - type: object properties: index: type: integer message: type: object properties: role: type: string const: assistant content: type: - string - 'null' tool_calls: type: array items: {} required: - role - content finish_reason: type: string enum: - stop - tool_calls - length - content_filter required: - index - message - finish_reason minItems: 1 maxItems: 1 additionalItems: false usage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer required: - prompt_tokens - completion_tokens - total_tokens required: - id - object - created - model - choices - usage - type: string text/event-stream: schema: type: string headers: Transfer-Encoding: required: true schema: type: string enum: - chunked '401': description: OpenAI-shaped error — bearer token missing, malformed, or revoked. content: application/json: schema: type: string examples: - error: message: Bearer token is missing, malformed, or revoked. type: authentication_error param: null code: invalid_api_key hasp_code: INVALID_API_KEY '403': $ref: '#/components/responses/AuthorizationException' '422': $ref: '#/components/responses/ValidationException' '429': description: OpenAI-shaped error — rate limit exceeded. content: application/json: schema: type: string examples: - error: message: Rate limit exceeded. type: rate_limit_error param: null code: rate_limited hasp_code: RATE_LIMITED components: schemas: ChatCompletionsRequest: type: object description: >- Validates POST /v1/chat/completions (OpenAI-compat) per ADR-YGE00M. Accepts OpenAI's Chat Completions wire format: system/user/assistant/tool role messages, function-tool definitions, and tool_calls/tool_call_id for round-tripping tool results. `top_p`, `tool_choice`, and `stop` are wired into InferenceRequest's canonical `topP`/`toolChoice`/`stopSequences` fields (HASP-509); `user` is forwarded as `metadata.user_id`, a documented graceful degrade on this surface (see DirectProviderDriver::supports()) — OpenAI's real API accepts it but HASP's OpenAI driver does not forward it upstream today. `n`, `frequency_penalty`, and `presence_penalty` are outside the cross-provider parameter model this DTO carries (no Anthropic analog) and remain validated for shape but otherwise ignored. properties: model: type: string maxLength: 100 tool_choice: type: - string - 'null' max_tokens: type: - integer - 'null' minimum: 1 maximum: 32000 stream: type: - boolean - 'null' temperature: type: - number - 'null' minimum: 0 maximum: 2 top_p: type: - number - 'null' minimum: 0 maximum: 1 'n': type: - integer - 'null' frequency_penalty: type: - number - 'null' minimum: -2 maximum: 2 presence_penalty: type: - number - 'null' minimum: -2 maximum: 2 user: type: - string - 'null' maxLength: 255 provider_extensions: type: - array - 'null' description: |- Escape hatch for provider-specific wire keys the canonical fields above don't (yet) model — see ADR-ZP99PX. No OpenAI driver wiring exists today (see DirectProviderDriver::supports()), so setting this is rejected with UNSUPPORTED_PARAMETER rather than silently dropped. items: type: string stop: type: - array - 'null' items: type: string messages: type: array items: type: object properties: role: type: string enum: - system - user - assistant - tool content: type: - string - 'null' name: type: - string - 'null' maxLength: 255 tool_call_id: type: - string - 'null' maxLength: 255 tool_calls: type: - array - 'null' items: type: object properties: id: type: string type: type: string enum: - function function: type: object properties: name: type: string arguments: type: string required: - name - arguments required: - id - type required: - role minItems: 1 tools: type: - array - 'null' items: type: object properties: type: type: string enum: - function function: type: object properties: name: type: string description: type: - string - 'null' parameters: type: - object - 'null' description: A JSON Schema object describing the function's parameters. additionalProperties: {} required: - name required: - type required: - model - messages title: ChatCompletionsRequest responses: AuthorizationException: description: Authorization error content: application/json: schema: type: object properties: message: type: string description: Error overview. required: - message ValidationException: description: Validation error content: application/json: schema: type: object properties: message: type: string description: Errors overview. errors: type: object description: A detailed description of each field that failed validation. additionalProperties: type: array items: type: string required: - message - errors securitySchemes: http: type: http scheme: bearer ````