Pricing
Deploying is free. Inference uses prepaid credits at the model's published token rates. You pay for tokens used, with no idle charges, minimum usage, or reserved-capacity fee. Rates are quoted per million tokens.
Model prices
Boardwalk benchmarks each serving configuration and derives its rates from measured throughput, infrastructure cost, and pricing assumptions. The model catalog and GET /v1/models show the active rates.
What you pay for
| Category | Billed tokens |
|---|---|
| Input | Uncached prompt tokens at the input rate. |
| Cache read | Prompt tokens served from the engine’s prefix cache. |
| Cache write | Tokens the engine reports writing to its cache. Free under automatic prefix caching. |
| Output | All generated tokens, including reasoning, at the output rate. |
If the engine does not report cache counts, the full prompt is billed as input and the receipt records that cache usage is unknown.
Rates are fixed for a configuration revision. A new price requires a new revision; past receipts keep their original rates. Traffic spikes do not change the price of a revision.
Add credits
Open Credits in the console to purchase credits and view your balance. Purchases start at $5, and credits never expire. New organizations start at zero. The organization making an API call pays for it, including calls to public models.
Auto top-up is off by default. Enable it to charge the card from your last purchase when a request leaves your balance below a chosen threshold. If the balance is insufficient, new inference requests return 402. Read-only organization data remains accessible.
Track spending
Charges use exact integer micro-dollars, rounded once on the request total. The console shows usage by model and individual request receipts. Each receipt records the billed tokens, exact rates, total cost, and serving revision.
Failed or disconnected inference requests are recorded at zero cost. Requests refused before reaching a model are also free. Tokenization is free.
See metering and receipts to verify a charge, or use the Organization API to export request history.