loading
loading
Pricing
Every model is priced in credits per 1M tokens. Billing is pay-as-you-go: each request bills straight against your credit balance, with no subscription or minimum.
4 enabled · credits per 1M tokens
context window · copied ids · live from the API
4 of 4 models · credits per 1M tokens
| Model | Input / 1M | Output / 1M |
|---|---|---|
Deepseek V4.1 Flash deepseek-v4.1-flash | 0.0145 | 0.041 |
Deepseek V4.1 Flash 10/17 deepseek-v4.1-flash-1017 | 0.021 | 0.083 |
Laguna S 2.1 free laguna-s-2.1:free | Free | Free |
Laguna XS 2.1 Free laguna-xs-2.1:free | Free | Free |
Prices are stored as Decimal(20,8) and printed without rounding. Input, output, cache reads and cache writes are priced per model; cached tokens bill their own rate. A free model is never charged.