ToolVet
75trust / 100

Chat Completions

by Omnia Odds in AI models & inference

x402 APIPassing, checked 4 h ago

OpenAI-compatible chat completions: POST messages[] with model fast (Llama 3.1 8B) or smart (Llama 3.3 70B), max_tokens, temperature; standard chat.completion response. Point any OpenAI SDK at this base URL. LLM inference for agents, no API key, no signup, pay per request

POST
https://odds.rjhsignaltech.workers.dev/v1/chat/completions
Price
$0.002
per call in USDC
Uptime
100%
last 30 days
Response time
592 ms
1.0 s slowest 5%
Last check
Passed
4 h ago, next any minute now

Run a free test callHow to call it

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to call it

POST https://odds.rjhsignaltech.workers.dev/v1/chat/completions

Each call costs $0.002 in USDC on Base, paid with the request over x402.

Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.

Example request

From the listing.

POST https://odds.rjhsignaltech.workers.dev/v1/chat/completions
content-type: application/json

{
  "max_tokens": 64,
  "messages": [
    {
      "content": "Give me three words that describe the Base network.",
      "role": "user"
    }
  ],
  "model": "fast"
}

Parameters

ParameterTypeRequiredDescription
max_tokensintegerNo
messagesarray of objectYes
modelstringNo"fast" (Llama 3.1 8B, default) or "smart" (Llama 3.3 70B)
temperaturenumberNo

Example response

The provider's example. We can't check it without paying.

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Fast, cheap, open.",
        "role": "assistant"
      }
    }
  ],
  "created": 1790268000,
  "id": "chatcmpl-1a2b3c",
  "model": "@cf/meta/llama-3.1-8b-instruct-fp8-fast",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 6,
    "prompt_tokens": 18,
    "total_tokens": 24
  }
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.002.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://odds.rjhsignaltech.workers.dev/v1/chat/completions' \
  -H 'content-type: application/json' \
  --data-raw '{"max_tokens":64,"messages":[{"content":"Give me three words that describe the Base network.","role":"user"}],"model":"fast"}'

# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://odds.rjhsignaltech.workers.dev/v1/chat/completions' \
  -H 'content-type: application/json' \
  --data-raw '{"max_tokens":64,"messages":[{"content":"Give me three words that describe the Base network.","role":"user"}],"model":"fast"}' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode
JavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

// Pays at most $0.002 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.002" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.002 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fodds.rjhsignaltech.workers.dev%2Fv1%2Fchat%2Fcompletions&method=POST
const res = await pay("https://odds.rjhsignaltech.workers.dev/v1/chat/completions", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({
    "max_tokens": 64,
    "messages": [
      {
        "content": "Give me three words that describe the Base network.",
        "role": "user"
      }
    ],
    "model": "fast"
  }),
});
console.log(res.status, await res.text());
Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client

# Pays at most $0.002 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.002"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.post(
        "https://odds.rjhsignaltech.workers.dev/v1/chat/completions",
        json={
            "max_tokens": 64,
            "messages": [
                {
                    "content": "Give me three words that describe the Base network.",
                    "role": "user",
                },
            ],
            "model": "fast",
        },
    )
    print(res.status_code, res.text)

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
4 h agoPassed402578 ms$0.002
9 h agoPassed4021.0 s$0.002
14 h agoPassed402874 ms$0.002
18 h agoPassed402782 ms$0.002
23 h agoPassed4021.0 s$0.002
Show 10 older checks
27 h agoPassed4021.2 s$0.002
31 h agoPassed4021.0 s$0.002
35 h agoPassed402789 ms$0.002
40 h agoPassed402792 ms$0.002
44 h agoPassed402457 ms$0.002
2 days agoPassed402725 ms$0.002
2 days agoPassed402760 ms$0.002
2 days agoPassed402566 ms$0.002
3 days agoPassed402629 ms$0.002
3 days agoPassed402624 ms$0.002