78trust / 100

Chat Completions

by gigsai in AI models & inference

x402 APIPassing, checked 59 min ago

Call when you need an LLM completion and have no API key: OpenAI-compatible chat completions (DeepSeek chat model), pay per call. Up to 16000 characters in, 512 tokens out, no streaming. Invalid requests are not charged.

POST https://gigsai.xyz/v1/chat/completions

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
460 ms typical, 618 ms slowest 5%
Last check
59 min ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://gigsai.xyz/v1/chat/completions" \
  -H "content-type: application/json" \
  -d '{"max_tokens":200,"messages":[{"content":"Summarise x402 in one sentence.","role":"user"}],"model":"deepseek-chat"}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fgigsai.xyz%2Fv1%2Fchat%2Fcompletions
const res = await pay("https://gigsai.xyz/v1/chat/completions", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"max_tokens":200,"messages":[{"content":"Summarise x402 in one sentence.","role":"user"}],"model":"deepseek-chat"}),
});
console.log(await res.json());

Example input

{
  "max_tokens": 200,
  "messages": [
    {
      "content": "Summarise x402 in one sentence.",
      "role": "user"
    }
  ],
  "model": "deepseek-chat"
}

Example output

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "pong",
        "role": "assistant"
      }
    }
  ],
  "model": "deepseek-chat",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 1,
    "prompt_tokens": 10,
    "total_tokens": 11
  }
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
59 min agoPassed402595 ms$0.002
5 h agoPassed402160 ms$0.002
8 h agoPassed402356 ms$0.002
12 h agoPassed402412 ms$0.002
15 h agoPassed402414 ms$0.002
19 h agoPassed402460 ms$0.002
23 h agoPassed402618 ms$0.002
26 h agoPassed402684 ms$0.002
31 h agoPassed402500 ms$0.002
34 h agoPassed402458 ms$0.002
37 h agoPassed402529 ms$0.002
42 h agoPassed402589 ms$0.002