Responses API: scope and limits

POST /responses is stateless: every request carries its whole input. It supports text input and instructions, function and custom tools (including namespaced tools and client tool search), MCP tools, structured output and streaming.

Endpoint: POST https://api.vani.ai/v1/responses
State: Stateless: store must be false
Output limit: max_output_tokens (see Output limits)
Streaming: stream: true (Responses events)

On this pageSupported

Supported

Text input (a string or message items with text parts) and instructions; full history including function_call, custom_tool_call and their outputs.
Function and custom tools, tool_choice, parallel_tool_calls, namespaced tools and client-executed tool search.
Structured output: text.format of type json_object or json_schema (name, schema up to 32 KiB, strict). The model is instructed to answer with JSON matching the schema; validate the result in your client.
MCP tools (see MCP tools on the API), reasoning.effort, metadata, user, safety_identifier, prompt_cache_key, service_tier auto/default (or priority where a fast model is listed).

Not supported

Stored state: store: true, previous_response_id, conversation, GET /responses/{id} and background mode are refused. Send the complete input on every call.
Hosted tools: web search, file search, image generation and computer use. Use function tools, or the media endpoints for images.
Image, audio and file input parts.
Encrypted reasoning items, reasoning summaries, top_logprobs, truncation other than disabled, max_tool_calls and prompt templates.

Note

An unsupported field is refused with 400 and named in the message (for example unsupported Responses field: top_logprobs); nothing is billed.

More reference: Model ids, limits, headers and usage · MCP tools on the API · Media API: images and videos · Artifacts API · API overview