
Beijing lab behind the Kimi models, known for long-context strength and agentic performance.
Compare Fast and Cheap modes, see the percentage saved, or filter to models with a verified discount. Select any model for its full pricing and API options.
Fast mode prioritizes response speed. Cheap mode uses lower-cost capacity and may be a little slower. Compare the same model’s input and output rates below.
| Model | Fast mode Input / output per 1M tokens | Cheap mode Input / output per 1M tokens | Discount | Run model |
|---|---|---|---|---|
| Kimi K3.1 ProMoonshot AI · 1.05M context | $2.1 / $10.5 | $0.2853 / $8.6634 | 17.5–86.4% off | |
| Kimi K3Moonshot AI · 1.05M context | $0.2016 / $16.8 | $0.1785 / $10.241 | 11.5–39% off | |
| Kimi K3 (batch)Moonshot AI · 1.05M context | $0.9629 / $6.3 | No verified discount | — | |
| Kimi K2.7 CodeMoonshot AI · 262K context | $0.63 / $3.675 | $0.63 / $3.15 | 0–14.3% off | |
| Kimi K2.6Moonshot AI · 262K context | $0.6825 / $3.5805 | $0.409 / $1.722 | 40.1–51.9% off | |
| Kimi K2.5Moonshot AI · 262K context | $0.5586 / $3.4913 | $0.5145 / $2.625 | 7.9–24.8% off | |
| Kimi K2 ThinkingMoonshot AI · 262K context | $0.63 / $2.625 | No verified discount | — | |
| Kimi K2 0905Moonshot AI · 262K context | $0.63 / $2.625 | No verified discount | — | |
| Kimi K2 0711Moonshot AI · 131K context | $0.5985 / $2.415 | No verified discount | — |
Discounts compare current uncached input and output rates. Different percentages mean savings depend on your token mix. Fast rates are routing ceilings; actual charges and capacity may vary. No discount is shown without a verified quote.