> ## Documentation Index > Fetch the complete documentation index at: https://impossibl.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create a response (OpenAI Responses API) > Implements OpenAI's Responses API for text. Set `stream: true` for semantic-event SSE. ## OpenAPI ````yaml /openapi.yaml post /v1/responses openapi: 3.1.0 info: title: Impossibl AI API version: 0.0.1 description: > The Impossibl AI API is one API for all AI providers, OpenAI-compatible across OpenAI, Anthropic, Google, xAI, and more (`GET /v1/models` lists the full catalog), billed from a prepaid credit balance. Provider usage is billed at provider list prices with no usage markup. Prepaid credit purchases charge a separate fixed 5% platform fee before tax. **Agent quickstart** 1. `POST /v1/accounts` — create a funded account; you get an API key and a signup-bonus balance in one call (no human step required). 2. Call `POST /v1/chat/completions`, `POST /v1/responses`, or `POST /v1/audio/transcriptions` with `Authorization: Bearer ` and a `provider/model` id from `GET /v1/models`. 3. Credits are deducted per request by token or audio-duration usage; check `GET /v1/account`. servers: - url: https://api.impossibl.com description: Production - url: http://localhost:8787 description: Local dev security: - BearerKey: [] paths: /v1/responses: post: summary: Create a response (OpenAI Responses API) description: >- Implements OpenAI's Responses API for text. Set `stream: true` for semantic-event SSE. operationId: createResponse requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ResponsesRequest' responses: '200': description: > A `response` object. When `stream: true`, the body is instead an SSE stream of `response.*` semantic events ending with `response.completed`. content: application/json: schema: $ref: '#/components/schemas/ResponseObject' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '402': $ref: '#/components/responses/InsufficientCredits' '404': $ref: '#/components/responses/UnknownModel' '502': $ref: '#/components/responses/UpstreamError' '503': $ref: '#/components/responses/ProviderNotConfigured' components: schemas: ResponsesRequest: type: object required: - model - input properties: model: type: string example: anthropic/claude-sonnet-4-5 input: oneOf: - type: string - type: array items: type: object description: >- A role message, or a `function_call` / `function_call_output` item on follow-up turns. properties: type: type: string enum: - message - function_call - function_call_output role: type: string enum: - system - developer - user - assistant content: description: >- A text string, or an array of input parts (input_text, input_image, input_audio). oneOf: - type: string - type: array items: $ref: '#/components/schemas/ResponsesInputContentPart' call_id: type: string description: Correlates a function_call and its function_call_output. name: type: string arguments: type: string description: JSON-encoded arguments string (on function_call). output: type: string description: Tool result text (on function_call_output). instructions: type: string stream: type: boolean default: false temperature: type: number top_p: type: number max_output_tokens: type: integer reasoning: type: object description: >- Stateless reasoning control. `summary` and stateful response chaining are not supported. properties: effort: type: string enum: - none - minimal - low - medium - high - xhigh nullable: true tools: type: array description: >- Function tools the model may call (relay mode). Function fields are flattened onto the tool. items: type: object required: - type - name properties: type: type: string const: function name: type: string description: type: string parameters: type: object description: JSON Schema for the tool input. strict: type: boolean tool_choice: description: '`auto`, `none`, `required`, or `{ type: function, name }`.' oneOf: - type: string enum: - auto - none - required - type: object properties: type: type: string const: function name: type: string ResponseObject: type: object description: Responses API object (`response`). properties: id: type: string example: resp_... object: type: string const: response created_at: type: integer status: type: string enum: - in_progress - completed - failed model: type: string output_text: type: string description: Convenience aggregation of the assistant text. output: type: array description: >- Output items — assistant `message` items and, on tool calls, `function_call` items. items: type: object properties: type: type: string enum: - message - function_call id: type: string status: type: string role: type: string const: assistant description: Present on `message` items. content: type: array description: Present on `message` items. items: type: object properties: type: type: string const: output_text text: type: string annotations: type: array items: type: object call_id: type: string description: Present on `function_call` items. name: type: string description: Present on `function_call` items. arguments: type: string description: >- Present on `function_call` items: JSON-encoded arguments string. usage: type: object properties: input_tokens: type: integer output_tokens: type: integer total_tokens: type: integer ResponsesInputContentPart: type: object properties: type: type: string enum: - input_text - input_image - input_audio text: type: string description: Present when `type` is `input_text`. image_url: description: >- Present when `type` is `input_image`: an http(s) URL or a `data:` URI, as a string or `{ url }`. oneOf: - type: string - type: object properties: url: type: string input_audio: type: object description: >- Present when `type` is `input_audio`. Only models advertising `audio` in `input_modalities` accept it. properties: data: type: string description: Base64-encoded audio (no data-URI prefix). format: type: string description: '`wav` or `mp3` (`aiff`, `aac`, `ogg`, `flac` also pass through).' Error: type: object properties: error: type: object properties: message: type: string type: type: string description: >- One of authentication_error, invalid_request_error, insufficient_quota, upstream_error, provider_not_configured. responses: BadRequest: description: Malformed request (bad JSON, or missing required fields). content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: '`model` and `messages` are required' type: invalid_request_error Unauthorized: description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Invalid API key type: authentication_error InsufficientCredits: description: The account's credit balance is empty. Top up to continue. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Insufficient credits. Top up to continue. type: insufficient_quota UnknownModel: description: The requested `model` id is not in the registry (see GET /v1/models). content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: 'Unknown model: foo/bar' type: invalid_request_error UpstreamError: description: The upstream provider returned an error. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: 'permission-denied: ...' type: upstream_error ProviderNotConfigured: description: The provider for this model has no API key configured on the gateway. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: 'Provider not configured: missing OPENAI_API_KEY' type: provider_not_configured securitySchemes: BearerKey: type: http scheme: bearer description: Gateway API key (`imp-rt-...`) from POST /v1/accounts or /v1/keys. ````