BYbytez

Responses

Sends input to an OpenAI compatible Responses model and returns a unified response object. Supports text and chat-style input, streaming, tools, and (for supported reasoning models) "thinking" via the reasoning object. To send a request to a closed source provider, prefix your model with their provider name, e.g. openai/gpt-5.1.

post/models/v2/openai/v1/responses

Request

Headers

Authorizationstring required

Token for authentication

Request body

modelstring required

The ID of the model to run (e.g., anthropic/claude-opus-4-5, openai/gpt-5.1)

max_output_tokensinteger

Maximum number of tokens to generate (counts reasoning + visible output for reasoning models)

temperaturenumber

Sampling temperature

streamboolean

Whether to stream SSE events

metadataobject

Arbitrary key/value metadata to attach to the request

userstring

End-user identifier (if supported)

includestring[]

Optional list of extra fields to include in the response (e.g. logprobs). Example values may include message.output_text.logprobs (provider/model dependent).

top_logprobsinteger

Number of most likely tokens to return at each position (if logprobs are included)

Example request

{
  "reasoning": {
    "effort": "medium"
  }
}

Response

Successful response

idstring required

Unique ID for this response

objectstring required

Type of returned object (usually response)

createdinteger required

Unix timestamp of response creation

modelstring required

Model used to generate the response

output_textstring

Convenience field containing concatenated output text (when applicable)

usageobject

Token usage details (shape may vary by provider)

Changes

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