{"service":"x402 inference gateway","what":"OpenAI-compatible chat completions + embeddings, paid per request in USDC via x402. No account, no API key.","endpoints":["POST https://agent-production-1daa.up.railway.app/v1/chat/completions","POST https://agent-production-1daa.up.railway.app/v1/embeddings"],"cache":{"rule":"deterministic requests (temperature 0; embeddings always) are cached — repeats bill at 55% of provider price (private per payer) or 35% with opt-in X-Cache-Scope: shared","controls":"X-Cache: bypass|force, X-Cache-Scope: shared, X-Cache-TTL: <seconds>","receipt":"X-Cache: HIT|MISS response header on every call"},"embedding_models_usd_per_mtok":{"text-embedding-3-small":{"input":0.02},"text-embedding-3-large":{"input":0.13}},"network":"eip155:8453","pricing":{"rule":"upstream cost x 1.04, billed on ACTUAL token usage (x402 'upto' scheme quotes a ceiling from max_tokens)","minimum_usd_per_call":0.001,"models_usd_per_mtok":{"gpt-5.4-nano":{"input":0.2,"output":1.25},"gpt-5.4-mini":{"input":0.75,"output":4.5},"gpt-5.4":{"input":2.5,"output":15},"gpt-5.5":{"input":5,"output":30},"gpt-4o-mini":{"input":0.15,"output":0.6},"gpt-4o":{"input":2.5,"output":10},"gpt-4.1-mini":{"input":0.4,"output":1.6},"gpt-4.1":{"input":2,"output":8}}},"quickstart":{"typescript":"const fetchWithPay = wrapFetchWithPayment(fetch, new x402Client().register('eip155:8453', new UptoEvmScheme(account))); await fetchWithPay('https://agent-production-1daa.up.railway.app/v1/chat/completions', { method: 'POST', headers: {'Content-Type': 'application/json'}, body: JSON.stringify({ model: 'gpt-5.4-nano', messages: [{ role: 'user', content: 'hello' }], max_tokens: 64 }) })","packages":"@x402/fetch @x402/evm viem","note":"Any x402-capable client works. Request body is standard OpenAI chat completions format; streaming and n>1 are not supported. Response headers X-Billed-Usd and X-Quoted-Ceiling-Usd show exact billing."},"limits":{"default_max_tokens":1024,"hard_max_tokens":8192}}