函数调用

POST

/v1/chat/completions

访问地址：https://koalaapi.com，OpenAI 兼容接口在末尾加 /v1。

Claude原生格式请求
模型名称：claude-opus-5-5、claude-sonnet-5-5、claude-sonnet-5、claude-opus-4-8、claude-opus-4-7、claude-sonnet-4-6、claude-haiku-4-5-20251001 等，以控制台【模型广场】为准

模型与官方文档

示例模型：claude-sonnet-4-6

本站在架模型（文本）：claude-opus-5-5、claude-sonnet-5-5、claude-sonnet-5、claude-opus-4-8、claude-opus-4-7、claude-sonnet-4-6、claude-haiku-4-5-20251001 等

厂商官网：Anthropic Claude 模型文档

说明：模型名称需与【模型广场】完全一致；不同令牌分组可用的模型不同，以控制台展示为准。

请求参数

Header 参数

Body 参数application/json必填

示例

{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "tools": [
        {
            "name": "get_weather",
            "description": "Get the current weather in a given location",
            "input_schema": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA"
                    }
                },
                "required": [
                    "location"
                ]
            }
        }
    ],
    "messages": [
        {
            "role": "user",
            "content": "What is the weather like in San Francisco?"
        }
    ]
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: sk-' \
--header 'Content-Type: application/json' \
--data '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "tools": [
        {
            "name": "get_weather",
            "description": "Get the current weather in a given location",
            "input_schema": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA"
                    }
                },
                "required": [
                    "location"
                ]
            }
        }
    ],
    "messages": [
        {
            "role": "user",
            "content": "What is the weather like in San Francisco?"
        }
    ]
}'

返回响应

🟢200成功

application/json

Bodyapplication/json

示例

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "model": "gpt-6.1-sol",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "string",
                "reasoning_content": "string",
                "tool_calls": [
                    {
                        "id": "string",
                        "type": "function",
                        "function": {
                            "name": "string",
                            "arguments": "string"
                        }
                    }
                ],
                "refusal": "string"
            },
            "finish_reason": "stop",
            "logprobs": {}
        }
    ],
    "usage": {
        "prompt_tokens": 0,
        "completion_tokens": 0,
        "total_tokens": 0,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "audio_tokens": 0
        },
        "completion_tokens_details": {
            "reasoning_tokens": 0,
            "audio_tokens": 0,
            "text_tokens": 0
        }
    },
    "system_fingerprint": "string",
    "service_tier": "string"
}

修改于 2026-11-06 09:34:37

文本生成 / 强制返回思考

Web search / 联网搜索

函数调用

模型与官方文档#

请求参数

请求示例代码

返回响应

模型与官方文档