79trust / 100

Chat Completions

by Private LLM Inference in AI models & inference

x402 APIPassing, checked 15 min ago

Privacy-first chat API: prompts run on a local open-weight model on dedicated hardware - your data is never forwarded to OpenAI/Anthropic or any third-party LLM cloud. OpenAI-compatible chat completions: summarize, draft, extract, translate, code, answer questions. Send a messages array, get chat.completion JSON. Pay per call in USDC on Base (x402), no API key or account. Tiers by output cap: quick 4,096 / long 8,192 / extended 32,768 tokens. Free trial: POST /v1/trial.

POST https://api.erb-llm.com/v1/chat/completions

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
659 ms typical, 797 ms slowest 5%
Last check
15 min ago
Next check
in 12 min

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://api.erb-llm.com/v1/chat/completions" \
  -H "content-type: application/json" \
  -d '{"messages":[{"content":"You are a helpful assistant.","role":"system"},{"content":"Reply with exactly one word: hello","role":"user"}],"model":"qwen/qwen3.8-27b","temperature":0.2}'
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%2Fapi.erb-llm.com%2Fv1%2Fchat%2Fcompletions
const res = await pay("https://api.erb-llm.com/v1/chat/completions", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"messages":[{"content":"You are a helpful assistant.","role":"system"},{"content":"Reply with exactly one word: hello","role":"user"}],"model":"qwen/qwen3.8-27b","temperature":0.2}),
});
console.log(await res.json());

Example input

{
  "messages": [
    {
      "content": "You are a helpful assistant.",
      "role": "system"
    },
    {
      "content": "Reply with exactly one word: hello",
      "role": "user"
    }
  ],
  "model": "qwen/qwen3.8-27b",
  "temperature": 0.2
}

Example output

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "hello",
        "role": "assistant"
      }
    }
  ],
  "id": "chatcmpl-abc123",
  "model": "qwen/qwen3.8-27b",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 1,
    "prompt_tokens": 30,
    "total_tokens": 31
  },
  "x402": {
    "charged": "$0.001",
    "inference_ms": 1830,
    "output_cap": 4096,
    "tier": "quick",
    "tokens_out": 1
  }
}

Security scan

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

Recent checks

WhenResultHTTPTimePrice
15 min agoPassed402614 ms$0.001
4 h agoPassed402636 ms$0.001
7 h agoPassed402560 ms$0.001
11 h agoPassed402736 ms$0.001
14 h agoPassed402825 ms$0.001
18 h agoPassed402659 ms$0.001
22 h agoPassed402768 ms$0.001
25 h agoPassed402679 ms$0.001
30 h agoPassed402636 ms$0.001
33 h agoPassed402705 ms$0.001
36 h agoPassed402577 ms$0.001
41 h agoPassed402797 ms$0.001