Claude Opus 4.8 API
Anthropic 提供支持的 Claude Opus 4.8 LLM 模型完整 API 参考。
模型变体
此 API 支持两个 Claude Opus 4.8 模型变体:
快速对比
Claude Opus 4.8 Text to Text
端点
POST /api/v1/chat/completions
请求参数
必填
消息支持
可选
示例请求
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Accept': 'text/event-stream',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'claude-opus-4.8-text-to-text',
messages: [
{
role: 'user',
content: 'Draft a technical decision memo for this architecture choice.'
}
],
stream: true,
max_tokens: 2048
})
});
Claude Opus 4.8 File Analysis
端点
POST /api/v1/chat/completions
请求参数
必填
消息支持
可选
示例请求
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Accept': 'text/event-stream',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'claude-opus-4.8-file-analysis',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Summarize this file and extract the key risks.' },
{
type: 'file',
file: {
filename: 'demo.pdf',
file_data: 'https://example.com/demo.pdf'
}
}
]
}
],
stream: true,
max_tokens: 4096
})
});
响应格式
Claude Opus 4.8 LLM 模型返回 OpenAI 兼容的 completion 响应。使用 stream: true 时,响应为 Server-Sent Events;使用 stream: false 时,响应为单个 JSON 对象。
成功响应
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"claude-opus-4.8-file-analysis","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"claude-opus-4.8-file-analysis","choices":[{"index":0,"delta":{"content":"Here is a concise summary"},"finish_reason":null}]}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"claude-opus-4.8-file-analysis","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"claude-opus-4.8-file-analysis","choices":[],"usage":{"prompt_tokens":12,"completion_tokens":8,"total_tokens":20}}
data: [DONE]
错误响应
event: error
data: {"error":{"message":"API requests too frequent, exceeding rate limit","type":"rate_limit_error","code":"1302","param":null}}
最佳实践
- 使用结构化消息: 通过
messages[] 发送对话历史,而不是把上下文压平成一个 prompt。
- 选择合适的模型变体: 纯文本推理和写作用 Text to Text,需要文件或图像时用 File Analysis。
- 消费 SSE 事件: 流式展示时追加
choices[0].delta.content,并将 data: [DONE] 视为成功完成。
- 仅发送支持的输入: 在当前客户端中,文本模型会忽略不支持的文件和图像部分。