GPT 6 API

请求参数

curl "https://apiany.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-6-astra",
  "messages": [
    {
      "role": "user",
      "content": "Analyze this fictional single-process JavaScript queue with two overlapping calls. let busy=false; const queue=['A','B']; async function take(){ if(busy || !queue.length) return; await Promise.resolve(); busy=true; const job=queue.shift(); try { await send(job); } finally { busy=false; } }. send(job) is async and must never overlap. Explain an interleaving that violates this rule, give the smallest safe fix, and describe a deterministic test. Do not redesign it into a distributed queue."
    }
  ],
  "temperature": 0.7,
  "max_tokens": 4096,
  "reasoning": {
    "summary": "auto"
  },
  "text": {
    "verbosity": "medium"
  }
}'

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "gpt-6-astra",
  "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
  }
}