◢ shipyard · inference
pay per call · usdc on solana · no subscription

Pay per call. Nothing else.

No seats, no tiers, no markup. Every request settles in USDC over x402 at the provider's own rate — and routing picks the cheapest capable model, so the price you see is the price after the savings.

$0.00
subscription fee
−71%
typical vs baseline
0%
gateway markup
Routed model rates — per 1M tokens, live from the gateway's candidate configs. These are the exact numbers routing decisions are made on.
ModelTierInput /1MOutput /1MContext
gpt-4.1-nanoeconomy$0.10$0.401.047576M
openai-main/gpt-4o-minieconomy$0.15$0.60128k
google-aistudio/gemini-3.1-flash-liteeconomy$0.25$1.501.048576M
claude-haiku-4-5economy$0.80$4.00200k
anthropic/claude-haiku-4-5-20251001economy$1.00$5.00200k
gpt-4.1-ministandard$0.40$1.601.047576M
google-aistudio/gemini-3.5-flash-litestandard$0.30$2.501.048576M
claude-sonnet-4-5standard$3.00$15.00200k
gpt-4.1frontier$2.00$8.001.047576M
openai-main/gpt-5frontier$1.25$10.00400k
anthropic/claude-sonnet-5frontier$2.00$10.001M

The baseline for savings is a direct call to claude-sonnet-4-5 — what the same request would cost at provider list price, called direct. Request model: auto and the gateway tiers down when a cheaper model can handle the work; pin a model and it stays pinned.

Spend ceilings, per key — a runaway agent can't drain you

Every API key carries its own spend breaker. When a key's recorded spend crosses its ceiling, it returns 402 with a top-up URL instead of quietly burning budget — and zero-cost local traffic never touches the breaker at all. Give each agent its own key so one drained session can't starve the others.

Settlement — USDC on Solana, over x402

Each request settles independently — no float, no invoice, no "Stripe, coming soon." Watch every cent land in real time on the live dashboard, or track your own key on the usage & ledger page.

Coming later: earn on the wait — sponsored placements on agent idle time. Advertiser? Get in early →