OpenAI Responses API subset on a SpicyAPI text model

Accepts the stateless subset of the OpenAI Responses API: model, input (string or item array with message, function_call and function_call_output items), instructions, max_output_tokens, temperature, top_p, tools (function tools), tool_choice, text.format, reasoning.effort and stream. The request is translated to a chat completion internally. previous_response_id is rejected with 400; send the full history in input instead. As on Chat Completions, sampling parameters the model does not declare are ignored and listed in the X-Spicy-Ignored-Params response header, and values outside the model's range or levels are changed to the nearest accepted value and listed in X-Spicy-Adjusted-Params.

Non-streaming calls return a response object with output[] (message and function_call items) and usage. Streaming calls emit response.created, response.output_text.delta and response.completed events.