API 参考文档

0. 快速开始

Base URL

https://hardysapi.com/v1

认证

所有请求需要在 Authorization 头中携带 Bearer Token：

Authorization: Bearer sk-hardy-YOUR_API_KEY

API Key 在 控制台 创建，格式 sk-hardy-...。

5 分钟迁移指南（OpenAI → HardysAPI）

# Python (openai 库)
from openai import OpenAI

client = OpenAI(
    api_key="sk-hardy-YOUR_KEY",     # ← 改
    base_url="https://hardysapi.com/v1", # ← 改
)

response = client.chat.completions.create(
    model="claude-opus-4-8",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

1. 端点列表

2. /v1/chat/completions

请求体

{
  "model": "claude-opus-4-8",       // 必填，模型 ID
  "messages": [                      // 必填，对话历史
    {"role": "system", "content": "你是助手"},
    {"role": "user", "content": "你好"},
    {"role": "assistant", "content": "你好！有什么可以帮助？"},
    {"role": "user", "content": "讲个笑话"}
  ],
  "max_tokens": 1024,                // 可选，默认 1024
  "temperature": 0.7,               // 可选，0-2，默认 1
  "top_p": 1,                       // 可选，0-1
  "stream": false,                    // 可选，默认 false，SSE
  "tools": [...],                    // 可选，function calling
  "tool_choice": "auto",            // 可选
  "user": "user-123"                 // 可选，用户追踪 ID
}

响应（非 streaming）

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "claude-opus-4-8",
  "choices": [{
    "index": 0,
    "message": {"role": "assistant", "content": "笑话：..."},
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 32,
    "completion_tokens": 128,
    "total_tokens": 160
  }
}

错误码

状态码	错误类型	说明
401	invalid_api_key	API Key 无效或过期
402	insufficient_balance	余额不足，请充值
404	model_not_found	模型不存在或暂不可用
429	rate_limit_exceeded	请求速率超限（每分钟 60-500 RPM 视套餐而定）
502	upstream_error	上游 API 错误，已自动重试 1 次
503	model_unavailable	模型暂不可用（上游限流或维护中）
529	overloaded	所有上游账号过载，建议 1 秒后重试

3. 支持的模型 (120+)

Anthropic Claude

claude-opus-4-8, claude-opus-4-8-1m-context, claude-sonnet-5, claude-haiku-4.5, claude-fable-5, claude-opus-4-7, claude-opus-4-6, claude-opus-4-5, claude-3-7-sonnet, claude-3-5-sonnet, claude-3-5-haiku, claude-3-opus

OpenAI GPT

gpt-5, gpt-5-codex, gpt-5.4, gpt-5.4-mini, gpt-5.5, gpt-5.5-openai-compact, gpt-5.6, gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-image-2, gpt-image-2-all, gpt-image-2-fast, o1-pro, o1-mini, codex-auto-review, codex-mini

Google Gemini

gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-image, gemini-2.5-flash-image-preview, gemini-2.5-flash-lite, gemini-2.5-flash-thinking, gemini-3-flash, gemini-3-pro-high, gemini-3-pro-low, gemini-3-pro-image, gemini-3-pro-preview, gemini-3.1-pro-high, gemini-3.1-pro-low, gemini-3.1-flash-image, gemini-3.1-flash-image-preview

xAI Grok

grok-4.3, grok-4.5, grok-build, grok-build-0.1, grok-imagine-image, grok-imagine-image-quality

国产模型

DeepSeek: deepseek-v3, deepseek-v4-flash, deepseek-v4-pro
Zhipu: glm-4.6, glm-4-flash
Moonshot: kimi-k2, kimi-latest
Xiaomi: mimo-v2.5-pro

4. Function Calling / Tools

完全兼容 OpenAI tools 协议：

{
  "model": "claude-opus-4-8",
  "messages": [...],
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "获取城市天气",
      "parameters": {
        "type": "object",
        "properties": {
          "city": {"type": "string"}
        },
        "required": ["city"]
      }
    }
  }],
  "tool_choice": "auto"
}

5. Streaming

设置 stream: true 即可获得 SSE 流式输出：

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1700000000,"model":"claude-opus-4-8","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1700000000,"model":"claude-opus-4-8","choices":[{"index":0,"delta":{"content":"你"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1700000000,"model":"claude-opus-4-8","choices":[{"index":0,"delta":{"content":"好"},"finish_reason":null}]}

...

data: [DONE]

6. 速率限制

套餐	RPM	TPM	并发
免费 / 默认	60	100K	3
付费用户	300	500K	10
企业版	500	1M	50
企业版 (申请)	2000+	5M+	100+