Responses

POST /v1/responses

Creates a model response for the given input. Compatible with the OpenAI Responses API.

Request body

Parameter	Type	Required	Description
model	string	Yes	Model ID to use
input	string | array	Yes	Text string (treated as user message) or array of input items
instructions	string	No	System/developer message injected into context
stream	boolean	No	Stream as SSE. Default: false
temperature	number	No	Sampling temperature, 0–2
top_p	number	No	Nucleus sampling, 0–1
max_output_tokens	integer	No	Upper bound for generated tokens
tools	array	No	Function tools the model may call
tool_choice	string | object	No	"none", "auto", "required", or specific tool
parallel_tool_calls	boolean	No	Allow parallel tool calls
reasoning	object	No	{ "effort": "low"|"medium"|"high", "summary": "auto"|"concise"|"detailed" }
truncation	string	No	"auto" (truncate to fit context) or "disabled"
previous_response_id	string	No	Continue a multi-turn conversation
store	boolean	No	Store response for later retrieval
metadata	object	No	Key-value pairs for tracking
text	object	No	Text response format config
seed	integer	No	Deterministic sampling seed
stop	string | string[]	No	Up to 4 stop sequences
top_k	integer	No	Top-k sampling (provider-specific)
repetition_penalty	number	No	Repetition penalty (provider-specific)

Input types

Simple string input:

{
  "model": "gpt-4o-mini",
  "input": "Explain quantum computing in one paragraph."
}

Structured input items:

{
  "model": "gpt-4o-mini",
  "input": [
    {
      "role": "user",
      "content": [
        { "type": "input_text", "text": "Describe this image" },
        { "type": "input_image", "image_url": "https://..." }
      ]
    }
  ]
}

Input item types:

• Message: { "role": "user"|"assistant"|"developer"|"system", "content": string | content[] }
• Function call output: { "type": "function_call_output", "call_id": "...", "output": "..." }
• Item reference: { "type": "item_reference", "id": "..." }

Content types: input_text, input_image, input_file

Response

{
  "id": "resp_abc123",
  "object": "response",
  "status": "completed",
  "created_at": 1700000000,
  "model": "gpt-4o-mini",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Quantum computing uses quantum bits (qubits)..."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 15,
    "output_tokens": 80,
    "total_tokens": 95
  }
}

Response status

Status	Description
completed	Generation finished successfully
failed	Generation failed (see error field)
in_progress	Still generating (streaming)
incomplete	Stopped early (see incomplete_details.reason)
cancelled	Request was cancelled
queued	Waiting to be processed

Usage object

Field	Type	Description
input_tokens	integer	Input tokens consumed
output_tokens	integer	Output tokens generated
total_tokens	integer	Total tokens
input_tokens_details	object	{ cached_tokens }
output_tokens_details	object	{ reasoning_tokens }

Multi-turn conversations

Use previous_response_id to continue a conversation without resending the full history:

{
  "model": "gpt-4o-mini",
  "input": "Now explain it to a 5-year-old.",
  "previous_response_id": "resp_abc123"
}