场景示意图，并非该模型生成结果
价格： 7.5 credits per 1K input tokens · ≈ $0.0037 · 37.5 credits per 1K output tokens · ≈ $0.0187稳定性高，并在 APIAny 平台提供详细的使用记录。
提示词预设，尚无生成结果
Sampling temperature.
Maximum output tokens.
Optional reasoning effort. Leave unset to use the model default. Higher effort can use more tokens and time.
美元估算 ≈ $0.077：$999 档换算：1 美元 = 2,000 积分。
历史记录
保存在此浏览器本地
0 个运行中 · 0 个已完成
输入
≈ $0.0037
输出
≈ $0.0187
缓存读取
≈ $0.0004
上下文
最大输出
鉴权
每个请求都需要在 Authorization 头中携带 Bearer 令牌。请在控制台创建 API Key。
Authorization: Bearer YOUR_API_KEYhttps://apiany.ai/v1/chat/completions请求参数
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
model | 字符串 | 必填 | 要调用的模型标识，使用该模型的 ID。 |
messages | 数组 | 必填 | OpenAI 对话格式的消息历史（role + content）。 |
stream | 布尔值 | 可选 | 为 true 时，响应将以 SSE 流式返回。 |
请求示例
curl "https://apiany.ai/v1/chat/completions" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-5",
"messages": [
{
"role": "user",
"content": "Review this fictional payment callback design. A signed event contains event_id and order_id. Handler verifies signature, reads order, sends a confirmation email, adds 100 credits, then marks order paid. Retries and simultaneous duplicate events are possible; database transactions are available. Identify idempotency and failure boundaries, recommend a minimal safe sequence and list tests. Do not assume email participates in a database transaction."
}
],
"temperature": 0.7,
"max_tokens": 4096,
"reasoning_effort": "high"
}'响应示例
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"model": "claude-opus-5",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 18,
"total_tokens": 30
}
}
