Responses

/api/v1/responses

Beta: This endpoint is currently in beta and may be unstable. Request/response schemas and behavior may change without notice. It is available to all API users.

Create a model response in OpenAI's Responses API format. Works with every Venice text model and returns typed output items such as reasoning, message, and function_call. Set stream: true to receive Server-Sent Events.

Most OpenAI models are forwarded to OpenAI's Responses API natively. Other models, and requests that use Venice features such as web search or characters, are translated through Chat Completions, where some Responses features are not supported. Send x-venice-responses-mode: native or compat to choose the mode, and read the x-venice-responses-lane response header to see which one served the request.

Venice does not store responses, so send the full conversation in input on every request. E2EE-capable models are not supported on this endpoint; use /api/v1/chat/completions with the required E2EE headers instead.

See the Responses API guide for the features and limitations of each mode.

Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.

post/api/v1/responses

Request

  • Base URL: https://api.venice.ai
  • URL: https://api.venice.ai/api/v1/responses
  • Auth: one of:
    • HTTP bearer
    • API key in header SIGN-IN-WITH-X

Request body

modelstring required

The ID of the model to use. E2EE-capable models are not supported on /api/v1/responses; use /api/v1/chat/completions with the required E2EE headers instead.

instructionsstring nullable

System instructions for the model, applied before input.

includestring[]

Additional response fields to include (OpenAI-compatible).

max_output_tokensinteger

Maximum number of tokens to generate.

temperaturenumber

Sampling temperature between 0 and 2.

top_pnumber

Nucleus sampling parameter.

parallel_tool_callsboolean

Whether the model may call more than one tool in a single turn.

prompt_cache_retention'in_memory' | '24h' | 'default' | 'extended'

Prompt cache retention for supported OpenAI models. "24h" or "extended" keeps cached prefixes for up to 24 hours.

web_searchboolean

Enable web search for this request.

streamboolean

Whether to stream back partial progress.

anon_user_idstring

Optional identifier for the API customer's end user. Combined with the Venice user id when attributing the request to upstream providers. Distinct from the discarded OpenAI user field. Must be printable ASCII and must not contain ||.

Example request

{
  "model": "zai-org-glm-5-1",
  "fallbacks": [
    {
      "model": "claude-opus-4-8"
    }
  ],
  "prompt_cache_retention": "24h",
  "anon_user_id": "end-user-123"
}

Response

Successful response

idstring required

Unique identifier for the response.

object'response' required

The object type.

created_atinteger required

Unix timestamp of when the response was created.

modelstring required

The model used for the response.

status'completed' | 'failed' | 'in_progress' | 'cancelled' | 'incomplete' required

The status of the response.

Example response

{
  "id": "resp_abc123"
}

Changes

No recorded changes to this operation across all 1 revision of this API.