
Chinese research lab famous for frontier-level open reasoning models at a fraction of typical cost.
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 |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017DeepSeek · 1.05M context | $0.0063 / $0.525 | No verified discount | — | |
| DeepSeek V4.1 Flash 1017 (batch)DeepSeek · 1.05M context | $0.0116 / $0.21 | No verified discount | — | |
| DeepSeek V4.1 FlashDeepSeek · 1.05M context | $0.0536 / $0.5954 | $0.0532 / $0.2129 | 0.6–64.2% off | |
| DeepSeek V4.1 Flash (batch)DeepSeek · 1.05M context | $0.0116 / $0.21 | No verified discount | — | |
| DeepSeek V4 Flash Vision ExpDeepSeek · 1.05M context | $0.462 / $1.386 | $0.2264 / $0.6791 | 51% off | |
| DeepSeek V4 Pro 0813DeepSeek · 1.05M context | $0.1166 / $4.662 | No verified discount | — | |
| DeepSeek V4 Flash 0731DeepSeek · 1.05M context | $0.0456 / $0.294 | No verified discount | — | |
| DeepSeek V4 Flash 0731 (batch)DeepSeek · 1.05M context | $0.0504 / $0.1512 | No verified discount | — | |
| DeepSeek V4 Pro 0423DeepSeek · 1.05M context | $0.2192 / $0.4385 | $0.2183 / $0.4365 | 0.4% off | |
| DeepSeek V4 Flash 0423DeepSeek · 1.05M context | $0.0956 / $0.1911 | $0.0294 / $0.0588 | 69.2% off | |
| DeepSeek V3.2DeepSeek · 164K context | $0.273 / $0.399 | $0.2192 / $0.3251 | 18.5–19.7% off | |
| DeepSeek V3.2 ExpDeepSeek · 164K context | $0.2835 / $0.4305 | No verified discount | — | |
| DeepSeek V3.1 TerminusDeepSeek · 164K context | $0.2835 / $1.05 | No verified discount | — | |
| R1 0528DeepSeek · 164K context | $0.525 / $2.2575 | No verified discount | — | |
| DeepSeek V3 0324DeepSeek · 164K context | $0.3045 / $1.197 | $0.2625 / $1.05 | 12.3–13.8% off |
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.