> ## Documentation Index > Fetch the complete documentation index at: https://dev-docs.altrum.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create a response > Sends a request in the OpenAI Responses format. Only create and stream are served: a stored response cannot be fetched, listed or deleted. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/responses openapi: 3.1.0 info: title: Altrum AI Gateway API version: 1.0.0 description: >- The public API of the Altrum AI Gateway. It accepts the OpenAI, Anthropic and Gemini request formats, so an existing client needs only a new base URL and a virtual key. servers: - url: https://api.altrum.ai security: - bearer: [] - apiKey: [] - googleApiKey: [] - altrumKey: [] tags: - name: OpenAI - name: Anthropic - name: Gemini - name: MCP - name: Health paths: /v1/responses: post: tags: - OpenAI summary: Create a response description: >- Sends a request in the OpenAI Responses format. Only create and stream are served: a stored response cannot be fetched, listed or deleted. operationId: createResponse parameters: - $ref: '#/components/parameters/RequestIdIn' - $ref: '#/components/parameters/PromptId' - $ref: '#/components/parameters/PromptVersion' - $ref: '#/components/parameters/CacheKey' - $ref: '#/components/parameters/CacheTtl' - $ref: '#/components/parameters/CacheThreshold' - $ref: '#/components/parameters/CacheType' - $ref: '#/components/parameters/CacheNoStore' - $ref: '#/components/parameters/DisableContentLogging' - $ref: '#/components/parameters/DirectKey' requestBody: required: true content: application/json: schema: type: object description: >- An OpenAI Responses request. Every other field the OpenAI API accepts is passed to the model. required: - model - input properties: model: type: string description: >- The provider and the model, such as `openai/gpt-4o-mini`. A name without a provider is matched to one your organization can serve. example: openai/gpt-4o-mini input: description: >- Text, or a list of input items, in the OpenAI Responses format. stream: type: boolean description: Stream the answer as server-sent events. fallbacks: type: array items: type: string description: >- Models to try in order when an attempt fails. Altrum's addition to the request body. additionalProperties: true example: model: openai/gpt-4o-mini input: Say hello. responses: '200': description: The response. headers: x-request-id: $ref: '#/components/headers/RequestId' x-alt-trace-id: $ref: '#/components/headers/TraceId' x-alt-provider: $ref: '#/components/headers/Provider' x-alt-resolved-model: $ref: '#/components/headers/ResolvedModel' x-alt-fallback-index: $ref: '#/components/headers/FallbackIndex' content: application/json: schema: type: object additionalProperties: true example: id: resp_123 object: response status: completed example: id: resp_123 object: response status: completed text/event-stream: schema: type: string description: >- Sent when the request asks to stream. Events keep the format of the API you called. '400': description: >- The request was refused: a guardrail stopped it, or the body or a header is not valid. headers: x-request-id: $ref: '#/components/headers/RequestId' content: application/json: schema: $ref: '#/components/schemas/OpenAIError' '401': description: No virtual key was sent, or the key does not exist or was revoked. headers: x-request-id: $ref: '#/components/headers/RequestId' content: application/json: schema: $ref: '#/components/schemas/OpenAIError' '402': description: A budget that covers this key is used up. headers: x-request-id: $ref: '#/components/headers/RequestId' content: application/json: schema: $ref: '#/components/schemas/OpenAIError' '403': description: >- The key, AI system, organization, model, provider or tool is not allowed. headers: x-request-id: $ref: '#/components/headers/RequestId' content: application/json: schema: $ref: '#/components/schemas/OpenAIError' '404': description: A prompt named in `x-alt-prompt-id` was not found. headers: x-request-id: $ref: '#/components/headers/RequestId' content: application/json: schema: $ref: '#/components/schemas/OpenAIError' '413': description: The request has more text than the guardrails can check at once. headers: x-request-id: $ref: '#/components/headers/RequestId' content: application/json: schema: $ref: '#/components/schemas/OpenAIError' '422': description: A guardrail stopped the reply. headers: x-request-id: $ref: '#/components/headers/RequestId' content: application/json: schema: $ref: '#/components/schemas/OpenAIError' '429': description: A rate limit that covers this key was reached. headers: x-request-id: $ref: '#/components/headers/RequestId' content: application/json: schema: $ref: '#/components/schemas/OpenAIError' '503': description: The guardrails could not be checked, or the provider is unavailable. headers: x-request-id: $ref: '#/components/headers/RequestId' content: application/json: schema: $ref: '#/components/schemas/OpenAIError' components: parameters: RequestIdIn: name: x-request-id in: header required: false description: >- Your own reference for the request. Altrum uses it instead of making one, and returns it. schema: type: string PromptId: name: x-alt-prompt-id in: header required: false description: >- Use a prompt saved in your AI Gateway prompts. Its messages go before yours. schema: type: string PromptVersion: name: x-alt-prompt-version in: header required: false description: The prompt version to use, such as `2`. Without it, the latest version. schema: type: integer CacheKey: name: x-alt-cache-key in: header required: false description: >- Keeps this request's cached answers apart from others, for example per customer. schema: type: string CacheTtl: name: x-alt-cache-ttl in: header required: false description: >- Keeps the answer for less time than your setting: `30s`, `5m`, `1h` or a number of seconds. schema: type: string example: 5m CacheThreshold: name: x-alt-cache-threshold in: header required: false description: Asks for a closer match than your setting, from 0 to 1. schema: type: number CacheType: name: x-alt-cache-type in: header required: false description: '`direct` matches word for word only, `semantic` by meaning only.' schema: type: string enum: - direct - semantic CacheNoStore: name: x-alt-cache-no-store in: header required: false description: >- `true` serves from the cache when it can, but does not store this answer. schema: type: string enum: - 'true' DisableContentLogging: name: x-alt-disable-content-logging in: header required: false description: >- `true` keeps this request's prompt and reply out of the request log, even when your organization keeps content. schema: type: string enum: - 'true' DirectKey: name: x-alt-direct-key in: header required: false description: >- `true` sends your own provider key in `Authorization`, `x-api-key` or `x-goog-api-key`, with your virtual key in `x-alt-vk`. Only when your organization allows it. schema: type: string enum: - 'true' headers: RequestId: description: The request's reference. Quote it to support. schema: type: string TraceId: description: The trace the request belongs to. schema: type: string Provider: description: The provider that answered. schema: type: string ResolvedModel: description: The model that answered. schema: type: string FallbackIndex: description: 'Present when a fallback answered: `1` for the first fallback.' schema: type: integer schemas: OpenAIError: type: object description: An error on the OpenAI routes. required: - error properties: type: $ref: '#/components/schemas/RefusalCode' is_gateway_error: type: boolean status_code: type: integer error: type: object properties: type: type: string code: type: string description: A refusal code or a stable code. message: type: string param: {} request_id: type: string extra_fields: type: object additionalProperties: true example: type: budget_exceeded is_gateway_error: true status_code: 402 error: type: budget_exceeded code: budget_exceeded message: 'Budget exceeded: ...' request_id: 4f9c... RefusalCode: type: string enum: - virtual_key_required - access_not_found - access_blocked - policy_access_denied - organization_inactive - gateway_disabled - ai_system_inactive - model_blocked - provider_blocked - mcp_tool_blocked - rate_limited - token_limited - request_limited - organization_concurrency_limit - budget_exceeded - access_unresolved - guardrail_blocked - response_blocked - guardrail_check_failed - payload_too_large - prompt_not_found - invalid_prompt_version description: Why Altrum refused the request. securitySchemes: bearer: type: http scheme: bearer description: >- Your virtual key, `sk-alt-...`. What every OpenAI and Anthropic SDK sends. apiKey: type: apiKey in: header name: x-api-key description: Your virtual key, as Anthropic clients send it. googleApiKey: type: apiKey in: header name: x-goog-api-key description: Your virtual key, as Gemini clients send it. altrumKey: type: apiKey in: header name: x-alt-vk description: >- Your virtual key. Needed when `Authorization` carries your own provider key (`x-alt-direct-key`). ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.