Reasoning · 6 models
Reasoning model API pricing
Models that think before they answer. Thinking tokens are billed as output tokens at the model’s output rate, and you can set how hard most of them think with reasoning_effort. One prepaid, OpenAI-compatible key calls every model below, from DeepSeek, OpenAI and Moonshot AI.
Reasoning models and prices
| Model | Context | Input$/1M | Cached$/1M | Output$/1M |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | 1M | $0.15 | $0.003 | $0.60 |
| GPT-6 Astra | 1.05M | $10.00 | $1.00 | $50.00 |
| GPT-6.1 Sol | 1.05M | $2.00 | $0.10 | $10.00 |
| GPT-6.1 Terra | 1.05M | $1.00 | $0.05 | $5.00 |
| Kimi K3.1 Pro | 1M | $1.92 | $0.192 | $10.04 |
| Kimi K3.1 Pro Highspeed | 1M | $3.84 | $0.192 | $20.08 |
Providers’ list prices in US dollars; the lowest input price here is $0.15 per 1M tokens. Tokens.Pay adds a 5% fee (minimum $0.79) when you add credit, never per request. How to use reasoning in the API.
More models
One key for every reasoning model.
From $5, plus a 5% top-up fee (minimum $0.79). No subscription; paid credit never expires.
Add credit