Model rates
How AUTO and provider model usage is priced per million tokens.
Model usage bills at the model's published per-million-token rate plus a 3% platform markup, rounded up.
Where rates come from
Input and output rates come from the published models.dev model catalog. That catalog is the versioned source: every entry carries the date it was last updated, and the platform reads the current catalog instead of a hand-maintained list. The machine-readable catalog is at models.dev/api.json.
Looking up a rate
A catalog entry prices one model at one provider. It reads as a model key and its rates, in US dollars per million tokens:
["togetherai/deepseek-ai/DeepSeek-V4.1-Flash", 0.3, 1.2, 0.006]togetherai/deepseek-ai/DeepSeek-V4.1-Flash- the provider and model key.0.3- the input rate.1.2- the output rate.0.006- the cache-read rate, listed only when the catalog publishes one.
In the catalog's own JSON the same entry reads cost.input, cost.output, and cost.cache_read. The catalog dated that entry 2026-09-10.
Rates change when a provider changes them, and the same model id can carry a different rate at a different provider, so look up your exact provider and model key in the current catalog.
Cached prompt tokens bill once, at the cache-read rate when the catalog publishes one and at the input rate when it does not. They are not also billed as input.
AUTO and AUTO-MAX
AUTO and AUTO-MAX route each request to an underlying model, and usage bills at the rates of the model that served it plus the platform markup, so both tiers cost what the serving model costs plus the markup.
A request that does not report the model that served it prices from the tier's own catalog entry. A model key the catalog no longer lists - for example a model an earlier release routed - is handled by the platform's pricing resolver, which prices it from a related catalog entry when one exists.
Other provider models
Other provider models use their published catalog rate plus the platform markup when a match exists.
BYOK requests
A BYOK request runs on a provider key or subscription you connected yourself. You pay that provider directly, so the platform does not charge the catalog token rate for that request.
Each request counts against your plan's monthly included BYOK requests. After that allowance the platform charges $1 per 1,000 requests ($0.001 per request) against the same wallet as other usage.
| Plan | Included BYOK requests per month |
|---|---|
| Hobby | 0 |
| Pro | 10,000 |
| Enterprise | No per-request fee |
Platform markup
Platform-managed model usage adds a 3% platform markup to the catalog price, recorded as MANAGED_MODEL_PLATFORM_FEE_MARKUP_BPS (300 basis points). The markup is applied when usage is rated, so a change applies only to new usage and already-recorded usage keeps the amount it was rated at.
The small minimum charge for usage with no catalog match is not marked up.
Fallback
If no catalog match exists, a small platform minimum charge applies per usage event. An event that reports no billable tokens is not charged.