DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V4 Flash 0731 (batch)deepseek/deepseek-v4-flash-0731:batch | DeepSeek |
69.1 | 1.04858M | $0.11 | $0.33 | — | ||
| DeepSeek: DeepSeek V4 Pro 0813 (batch)deepseek/deepseek-v4-pro-0813:batch | DeepSeek |
68.8 | 1.04858M | $0.66 | $1.98 | — | ||
| DeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus | DeepSeek |
43.5 | 131.072K | $0.27 | $1 | — | ||
| DeepSeek: DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 | DeepSeek |
21.2 | 163.84K | $0.25 | $1 | — |