Responses
OpenAI Responses–compatible endpoint on the Modellix LLM gateway. Accepts a synchronous request with model (provider/name format) and input (string or content array); returns a Responses JSON object by default, or SSE (text/event-stream) when stream=true. Use max_output_tokens for output limits. Prefer this path when the client targets the OpenAI Responses API rather than classic Chat Completions. Do not send Chat Completions-style messages/max_tokens or Anthropic Messages shapes on this endpoint—use /chat/completions or /messages instead. Optional fields follow OpenAI Responses; support depends on the selected model.
Authorizations
Authorization: Bearer (OpenAI SDK, Codex, OpenCode, etc.)
Headers
Optional session affinity header. Length 8–128; alphanumeric, -, and _ only.
8 - 128^[A-Za-z0-9_-]+$"my-conversation-001"
Body
OpenAI Responses request body. Requires model and input; optional stream, max_output_tokens, and temperature. Do not send Chat Completions messages.
Core fields below; other fields follow OpenAI Responses.
Model ID in provider/name form
"openai/gpt-5.5"
"openai/gpt-5.6-sol"
"anthropic/claude-sonnet-5"
"google/gemini-3.6-flash"
String or content array for the Responses API. Not a Chat Completions messages array.
Default false. When true, returns an OpenAI Responses SSE event stream.
Optional maximum output tokens for the Responses API. Not max_tokens.
x >= 1Sampling temperature for the Responses API. Model-dependent.
Response
Success. Non-streaming returns JSON; streaming returns SSE.
Shape follows OpenAI response
Unique identifier for this Responses API result.
Object type. Typically response for the Responses API.
"response"
Status of the response (for example completed or failed).
Model ID that produced this Responses API result.
Array of response output items (OpenAI Responses shape).
Token usage object for the Responses API. Shape follows OpenAI Responses usage, not Chat Completions prompt_tokens fields.