Jiniu AIJiniu AI
Docs
ChatNative OpenAI format

Responses format

OpenAI Responses API for creating model responses. Supports multi-turn conversations, tool calls and reasoning.

POST
/v1/responses

Request Body

application/json

model*string

Model name; must match the identifier in the model catalog exactly

input?string|

Input, either a string or an array of messages

instructions?string

System-level instructions placed at the front of the context; they are not inherited when previous_response_id is used

max_output_tokens?integer

Token cap for the generated content, counting both visible output and reasoning tokens

temperature?number

Sampling temperature. Higher values give more varied output; typically 0–2. Tune this or top_p, not both

top_p?number

Nucleus sampling: sample only from candidates within this cumulative probability. Tune this or temperature, not both

stream?boolean

Whether to stream the response over SSE

tools?

Tools the model may call

tool_choice?string|

Tool choice: auto, none, or a specific tool

reasoning?

Settings for reasoning models, such as effort and summary

previous_response_id?string

Previous response ID, used to continue a multi-turn conversation

truncation?string

Truncation strategy when the context overflows: auto drops middle content, disabled raises an error

Value in"auto" | "disabled"

Response Body

application/json

curl -X POST "https://jiniu.ai/v1/responses" \  -H "Content-Type: application/json" \  -d '{    "model": "string"  }'
{
  "id": "string",
  "object": "response",
  "created_at": 0,
  "status": "completed",
  "model": "string",
  "output": [
    {
      "type": "string",
      "id": "string",
      "status": "string",
      "role": "string",
      "content": [
        {
          "type": "string",
          "text": "string"
        }
      ]
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0
    }
  }
}