SERVICE

ai-chat

Xynaptic AI Chat — LLM inference pay-per-call: OpenAI-compatible messages, model auto-routing (glm-5.3-flash / deepseek-v4.1-flash), JSON response with token usage. POST with body: {"model": "auto", "messages": [{"role": "user", "content": "..."}]}.

$0.02 per call · /v1/ai-chat

Or subscribe: $4/month on this service alone, about 285 calls included, POST /v1/sub-buy {"plan":"svc-ai-chat"}.

Call it

curl -s https://api.xynaptic.io/v1/ai-chat \
  -H "Accept: application/json"

# -> 402 Payment Required (x402 challenge: price, payTo, networks)
# -> sign the payment, retry with PAYMENT-SIGNATURE -> 200

What you get back

{
  "id": "xyn-chat-8f3c1a9b2e",
  "object": "chat.completion",
  "created": 1762725600,
  "model": "glm-5.3-flash",
  "system_fingerprint": "xynaptic-v2.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here is a direct answer to your question, using only the provided data."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 812,
    "completion_tokens": 96,
    "total_tokens": 908
  },
  "service": "ai-chat",
  "question": "Example request",
  "summary": "chat analysis: LLM synthesis",
  "tools": [],
  "xynaptic": {
    "service": "chat",
    "provider": "zai",
    "model_requested": "auto",
    "model_used": "glm-5.3-flash",
    "routing": "direct",
    "fallback_used": false
  }
}