Inference

Last 30 days

Uptime

100%

Response time

48 ms typical, 64 ms slowest 5%

Last check

4 h ago

Next check

any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://api.oblique.markets/api/v1/paid/inference" \
  -H "content-type: application/json" \
  -d '{"messages":[{"content":"Say hello in five words.","role":"user"}]}'

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.oblique.markets%2Fapi%2Fv1%2Fpaid%2Finference
const res = await pay("https://api.oblique.markets/api/v1/paid/inference", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"messages":[{"content":"Say hello in five words.","role":"user"}]}),
});
console.log(await res.json());

Example input

{
  "messages": [
    {
      "content": "Say hello in five words.",
      "role": "user"
    }
  ]
}

Example output

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello! How can I help you?",
        "role": "assistant"
      }
    }
  ],
  "created": 1789171942,
  "id": "gen-1789171942-4eZlZ1R9FNzHB7l9nTCc",
  "model": "deepseek/deepseek-v4-flash",
  "object": "chat.completion",
  "payment_info": {
    "authorized_max_usdc": 0.01,
    "charged_usdc": 0.01,
    "message": "Fixed-price payment settled via x402 protocol",
    "payment_scheme": "exact",
    "usage_cost_estimate_usd": 0.000011
  },
  "usage": {
    "completion_tokens": 9,
    "cost": 0.00000252,
    "prompt_tokens": 10,
    "total_tokens": 19
  }
}

Security scan

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

Recent checks