Source: https://aiprimetech.io/zh/docs/api-reference/models-endpoint/

[首页](/zh/) / [文档](/zh/docs/) / 模型端点 

# 模型端点 

GET /v1/models——准确了解您的密钥可调用哪些模型 ID。 

 复制页面 [ 以 Markdown 查看](/zh/docs/api-reference/models-endpoint.md) [ 向 ChatGPT 提问](https://chatgpt.com/?q=Read%20https%3A//aiprimetech.io/docs/api-reference/models-endpoint.md%20and%20answer%20questions%20about%20it.%20Start%20with%20a%20short%20summary.) [ 在 Claude 中提问](https://claude.ai/new?q=Read%20https%3A//aiprimetech.io/docs/api-reference/models-endpoint.md%20and%20answer%20questions%20about%20it.%20Start%20with%20a%20short%20summary.)   

权威列表。如果某个 ID 不在此列表中，您的密钥就无法调用它——不要根据文档或博客文章猜测 ID。 

```
Copycurl https://aiprimetech.io/v1/models \
  -H "Authorization: Bearer $CLAUDEAPIKEY"
```

## 响应 

```
Copy{
  "object": "list",
  "data": [
    {"id": "claude-opus-4-8",   "object": "model", "owned_by": "anthropic"},
    {"id": "claude-sonnet-4-6", "object": "model", "owned_by": "anthropic"},
    {"id": "gpt-5.5",           "object": "model", "owned_by": "openai"}
  ]
}
```

## 实际用途 
- 健康检查。 200 可证明基础 URL 和密钥均正确，之后再排查其他问题。
- 填充模型选择器。 在启动时读取 ID，而不是硬编码一个会过时的列表。
- 发现拼写错误。 根据此列表验证配置的模型 ID，并在启动时明确报错，而不是等到用户首次请求时才报错。 

```
Copyimport os, httpx

r = httpx.get(
    class="s">"https://aiprimetech.io/v1/models",
    headers={class="s">"Authorization": fclass="s">"Bearer {os.environ['CLAUDEAPIKEY']}"},
    timeout=20,
)
r.raise_for_status()
ids = [m[class="s">"id"] for m in r.json()[class="s">"data"]]
assert class="s">"claude-sonnet-4-6" in ids, class="s">"configured model not available on this key"
```

[模型价格与上下文窗口](/zh/docs/getting-started/models/)[错误model_not_found 的含义](/zh/docs/api-reference/errors/) 

[上一页聊天补全 API](/zh/docs/api-reference/chat-completions/)[下一页流式传输](/zh/docs/api-reference/streaming/)