Chat Completions

Create a chat completion using the OpenAI-compatible format. Text input only; supports both streaming (stream:true, SSE) and non-streaming responses.

POSThttps://api.longcat.chat/openai/v1/chat/completions

Authorizations

Authorizationstringheaderrequired

Authentication key, passed in the request header as Bearer YOUR_API_KEY.

default: false

Bodyapplication/json

modelstringrequired

Model identifier. Currently supports LongCat-2.0-Preview.

default: false

messagesarrayrequired

Array of message objects. Text input only.

default: false

rolestringrequired

Author role, one of system · user · assistant.

default: false

contentstringrequired

Message content as a plain-text string.

default: false

streambooleanoptional

Whether to stream the response as SSE.

default: false

max_tokensintegeroptional

Maximum number of tokens to generate. LongCat-2.0-Preview max is 131072 (128K).

default: 32768

temperaturenumberoptional

Sampling temperature, range 0 ~ 1.

default: false

top_pnumberoptional

Nucleus sampling parameter.

default: false

thinkingobjectoptional

Whether to enable thinking. {"type":"enabled"} turns thinking on, {"type":"disabled"} turns it off.

default: false

Request

cURL

Basic

bash

curl --location --request POST 'https://api.longcat.chat/openai/v1/chat/completions' \
  --header "Authorization: Bearer $LONGCAT_API_KEY" \
  --header "Content-Type: application/json" \
  --data-raw '{
    "model": "LongCat-2.0-Preview",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "Hello!" }
    ],
    "max_tokens": 1024,
    "temperature": 0.7,
    "thinking": {
      "type": "enabled"
    }
  }'

Response

JSON

json

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "LongCat-2.0-Preview",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?",
        "reasoning_content": "\nThe user is simply greeting me and asking how I am - this is a basic conversational opener. I should respond in a friendly, helpful manner while staying true to my character as OWL. I should acknowledge the greeting, express that I'm doing well, and offer to help them with whatever they need. This is a straightforward interaction that doesn't require any complex reasoning or special handling."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 15,
    "total_tokens": 35,
    "completion_tokens_details": {
      "reasoning_tokens": 78
    }
  }
}