DeepSeek V4 API

Request-Parameter

curl "https://apiany.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v4",
  "messages": [
    {
      "role": "user",
      "content": "Compare a queue and a synchronous endpoint for this fictional service: image processing takes 20-60 seconds, traffic bursts to 100 requests/second for 2 minutes, clients can poll, jobs must survive restarts, and two engineers have two weeks. Acknowledge partial failures and retries. Recommend the smaller viable design with acceptance criteria; do not invent traffic beyond the supplied facts."
    }
  ],
  "temperature": 0.7,
  "max_tokens": 4096
}'

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "deepseek-v4",
  "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
  }
}