Create Thinking Chat [Native Format]

Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position. Create a completion for the provided prompt and parameters Official Documentation: https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking

Endpoint

POST http://v98store.com/v1/messages

cURL Command

curl -X POST 'http://v98store.com/v1/messages' \ -H 'Content-Type: application/json' \ -H 'Authorization: Bearer YOUR_TOKEN' \ -d '{ "model": "claude-sonnet-4-20250514", "system": "你Yes一 智能AI助手,叫小王", "messages": [ { "role": "user", "content": "你Yes谁?!" } ], "stream": true, "max_tokens": 8000, "thinking": { "type": "enabled", "budget_tokens": 1200 } }'

Parameters

NameInDescriptionRequired
Content-TypeheaderYes
AcceptheaderYes
AuthorizationheaderNo

Request Body

Example

{
  "model": "claude-sonnet-4-20250514",
  "system": "你Yes一 智能AI助手,叫小王",
  "messages": [
    {
      "role": "user",
      "content": "你Yes谁?!"
    }
  ],
  "stream": true,
  "max_tokens": 8000,
  "thinking": {
    "type": "enabled",
    "budget_tokens": 1200
  }
}

Responses

200 -

Example

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\nHello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}