72trust / 100

Chat Completions

by Chat completions - premium tier in AI models & inference

x402 APIPassing, checked 1 h ago

OpenAI-compatible chat completions, premium tier: gpt-5, gpt-6 astra, o3 and o4-mini, claude opus, claude fable 5.1 - paid per call in USDC over x402. Same wire format as /v1/chat/completions with the largest caps (85k chars in, 8192 tokens out).

POST
https://agent402.tools/v1/premium/chat/completions
Price
$0.5
per call in USDC
Uptime
100%
last 30 days
Response time
317 ms
421 ms slowest 5%
Last check
Passed
1 h ago, next in 5 h

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://agent402.tools/v1/premium/chat/completions

Each call costs $0.5 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://agent402.tools/v1/premium/chat/completions
content-type: application/json

{
  "max_tokens": 5,
  "messages": [
    {
      "content": "Reply with exactly: OK",
      "role": "user"
    }
  ],
  "model": "anthropic/claude-opus-4"
}

Parameters

ParameterTypeRequiredDescription
cache_controlanyNoOptional - prompt caching preference. Default ON ({type:"ephemeral"}, 5-minute TTL): repeated prefixes across your turns are served from the provider cache (same price to you). Send false to disable. ttl:"1h" is not offered.
max_completion_tokensintegerNoOptional - alias of max_tokens (newer OpenAI SDKs send this).
max_tokensnumberNoOutput token cap (clamped to the tier maximum)
messagesarrayYesOpenAI chat messages: [{role, content}] - text and image_url content blocks supported
modelstringYesModel id - OpenRouter form (openai/gpt-4o-mini) or bare OpenAI form (gpt-4o-mini). GET /v1/models lists the allowlist per tier. Optional: omit it and the tier serves its documented default (x402.defaultModel on /v1/models), named back in agent402_default_model; the price does not change
reasoningobjectNoOptional - {effort: "none"|"minimal"|"low"|"medium"|"high"|"xhigh"|"max", max_tokens?, exclude?, enabled?}. Reasoning tokens count against max_tokens. Omitted: low effort on the budget tiers, the model default on premium. reasoning_effort (string) is accepted as an alias.
toolsarrayNoOptional - OpenAI function tools {type:"function", function:{...}}, or a tool namespace {type:"namespace", name, tools:[...]} (flattened into its functions). The pro and premium routes also accept the bounded server tools openrouter:web_search, openrouter:web_fetch and openrouter:datetime with serv…
zdrbooleanNoOptional - true routes only to zero-data-retention providers (OpenRouter provider.zdr); the only provider preference a caller may set.

Example response

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

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "OK",
        "role": "assistant"
      }
    }
  ],
  "created": 1750000000,
  "id": "gen-…",
  "model": "anthropic/claude-opus-4",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 1,
    "prompt_tokens": 12,
    "total_tokens": 13
  }
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.5.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://agent402.tools/v1/premium/chat/completions' \
  -H 'content-type: application/json' \
  --data-raw '{"max_tokens":5,"messages":[{"content":"Reply with exactly: OK","role":"user"}],"model":"anthropic/claude-opus-4"}'

# 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://agent402.tools/v1/premium/chat/completions' \
  -H 'content-type: application/json' \
  --data-raw '{"max_tokens":5,"messages":[{"content":"Reply with exactly: OK","role":"user"}],"model":"anthropic/claude-opus-4"}' \
  | 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 $0.5 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.5" });
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 $0.5 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fagent402.tools%2Fv1%2Fpremium%2Fchat%2Fcompletions&method=POST
const res = await pay("https://agent402.tools/v1/premium/chat/completions", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({
    "max_tokens": 5,
    "messages": [
      {
        "content": "Reply with exactly: OK",
        "role": "user"
      }
    ],
    "model": "anthropic/claude-opus-4"
  }),
});
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 $0.5 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.5"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.post(
        "https://agent402.tools/v1/premium/chat/completions",
        json={
            "max_tokens": 5,
            "messages": [
                {
                    "content": "Reply with exactly: OK",
                    "role": "user",
                },
            ],
            "model": "anthropic/claude-opus-4",
        },
    )
    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
1 h agoPassed402195 ms$0.5
11 h agoPassed402262 ms$0.5
21 h agoPassed402194 ms$0.5
31 h agoPassed402190 ms$0.5
40 h agoPassed402347 ms$0.5
Show 10 older checks
2 days agoPassed402528 ms$0.5
2 days agoPassed402184 ms$0.5
3 days agoPassed402328 ms$0.5
3 days agoPassed402189 ms$0.5
4 days agoPassed402259 ms$0.5
4 days agoPassed402604 ms$0.5
4 days agoPassed402288 ms$0.5
4 days agoPassed402346 ms$0.5
5 days agoPassed402322 ms$0.5
5 days agoPassed402298 ms$0.5