Pricing
Prices are generated from the live catalog: this table is what the platform charges, to the token, with nothing else on the bill.
| Model | Context | $/1M in | $/1M out | $/1M cached |
|---|---|---|---|---|
| Qwen | ||||
| qwen3.8-27b | 262K | $0.35 | $2.55 | $0.105 |
| qwen3.6-35b | 131K | $0.11 | $0.8 | $0.044 |
| Minimax | ||||
| minimax-m2.7 | 197K | $0.24 | $0.95 | $0.072 |
| Muse | ||||
| muse-glimmer-30b | 131K | $0.28 | $1.2 | $0.084 |
| Ornith | ||||
| ornith-1.5-35b | 100K | $0.35 | $2.55 | $0.105 |
| ornith-1.5-9b | 100K | $0.1 | $0.3 | $0.03 |
| Glm | ||||
| glm-5.3-flash | 1049K | $0.11 | $0.35 | $0.033 |
| Deepseek | ||||
| deepseek-v4-flash-0731 | 1311K | $0.15 | $0.42 | $0.045 |
| Gemma | ||||
| gemma-4-31b-it | 262K | $0.22 | $0.49 | $0.066 |
| Deepseek | ||||
| deepseek-v4-pro | 1000K | $1.13 | $2.21 | $0.339 |
| Chatterbox | ||||
| chatterbox-tts | — | $25/1M chars | ||
| Kokoro | ||||
| kokoro-tts | — | $15/1M chars | ||
| pocket-tts | — | $16/1M chars | ||
| Audio | ||||
| audio8-tts | — | $8/1M chars | ||
| Hayamimi | ||||
| hayamimi-stt | — | $0.6/audio-hr | ||
| Bge | ||||
| bge-m3 | — | $0.05/1M tokens | ||
| bge-reranker-v2-m3 | — | $1.5/1k searches | ||
| Whisper | ||||
| whisper | — | $0.25/audio-hr | ||
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_tokensand 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
qwen3.8-27bandmuse-glimmer-30bat the same token rates (image parts count as input tokens).
Variant aliases (a -fast tier, for instance) appear on this table the moment they are listed; unlisted variants are never served a price row they were not promised.
What the platform commits to
Three of our beta commitments are price-relevant, stated here in those words:
- Prepaid wallet = hard cap. Your wallet cannot go negative: runaway billing is structurally impossible.
- Price you see is price you pay, no credit-load fees. Credits are charged at face value.
- No mid-term changes to purchased credits. Bought credits keep their terms.
All five commitments live on the beta commitments page.