openai-compatible · one endpoint · x402 settlement

The inference layer that pays for itself.

One endpoint in front of every model — routed to the cheapest capable provider, failed over when one blinks, billed per call in USDC. No subscription, no markup — just cheaper, more reliable inference.

01 — route

The cheapest capable model. Every call.

Auto-tiering per request, circuit breakers per provider, a failover receipt on every response. Typically 70%+ under baseline — and your own model stays yours; routing is opt-in.

livesettled on solana
claude-code / a91fgpt-5-nano ← failover−71%saved
hermes / 4d20claude-haiku-4.5−58%saved
dock-mate / 77c3auto → llama-4-scout−84%saved
02 — reliability

When a provider blinks, you don't.

Circuit breakers per provider, health tracking, and automatic failover to the next rung — with the full receipt on every response. Your agent never sees a provider outage; it just sees an answer.

Request model: auto and the gateway tiers, costs, and fails over for you — pinned models stay pinned, and local Ollama traffic always runs free.

failover receiptsx_shipyard
openainouscircuit open312msok
gpt-5-mininanotier: refactor−71%ok
local / ollamafree tier$0.00free
03 — models

One endpoint. Every model.

Drop-in for anything that speaks OpenAI — Claude Code, your own agents, plain curl. Anthropic, OpenAI, OpenRouter, UsePod, and Nous/Hermes behind one interface, plus your local models for free. Keep your own model and API keys; routing is strictly opt-in.

# issues an sk-shipyard key + a status line — model untouched npx shipyard-inference connect --url https://shipyard-inference.vercel.app
from openai import OpenAI client = OpenAI( base_url="https://shipyard-inference.vercel.app/v1", api_key="sk-shipyard-…", # your key from `connect` ) resp = client.chat.completions.create( model="auto", # cheapest capable model, chosen per call messages=[{"role": "user", "content": "hello from my agent"}], ) print(resp.choices[0].message.content)
# or curl it directly curl https://shipyard-inference.vercel.app/v1/chat/completions \ -H "authorization: Bearer ***" \ -H "content-type: application/json" \ -d '{"model":"auto","messages":[{"role":"user","content":"hi"}]}'
04 — pricing

Pay per call. Nothing else.

No subscription, no seat fees, no markup. Every call settles in USDC over x402 at the provider's own rate, with spend ceilings per key so a runaway agent can't drain you. What you see in the ledger is what you paid.

your ledgersettled on solana
cost this week$0.412paid
saved vs baseline$9.86−71%
subscription fee$0.00never
05 — connect

Change one URL. Keep your model.

# issues an sk-shipyard key + a status line — model untouched npx shipyard-inference connect --url https://shipyard-inference.vercel.app