Pricing

The live catalog generates every price on this page. The table is what the platform charges, to the token. Nothing else lands on the bill.

How pricing works

• Per-token, per-model. Input tokens, output tokens, and cached-input tokens bill at the three rates in the table above: no per-request fee, no minimum, no monthly line item.
• Cache reads bill at the cached rate. Prompt-prefix cache hits are reported in usage.prompt_tokens_details.cached_tokens and billed at the cached column, not the input column.
• Thinking tokens bill as output. On models that emit reasoning (for example the MiniMax family), hidden thinking tokens are billed as output tokens and are visible in usage.completion_tokens_details.reasoning_tokens: the number you are charged for is the number you can audit.
• Vision is available on qwen3.8-27b and muse-glimmer-30b at the same token rates (image parts count as input tokens).
• Bonus credits work on most, not all, models. Credits from the 2-for-1 match are spent before your purchased credits on the models they cover; the covered list lives on the console's billing page, generated from the live catalog (never typed here). A wallet holding only match credits calling any other model gets a 402 promo_credits_not_valid_for_model before anything is charged: top up purchased credits (they work on every model) or call a covered model. Detail on the errors page.

A variant alias, such as a -fast tier, appears on this table the moment it is listed. An unlisted variant never gets a price row. It was not promised one.

What the platform commits to

Three of our beta commitments touch price. They are restated here in those words:

1. Prepaid wallet = hard cap. Your wallet cannot go negative: runaway billing is structurally impossible.
2. Price you see is price you pay, no credit-load fees. Credits are charged at face value.
3. No mid-term changes to purchased credits. Bought credits keep their terms.

All five commitments live on the beta commitments page.