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.
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
43 providers
Open MoE flagship with million-token context for coding and long agent runs
62 providers
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
62 providers
DeepSeek chat model for instruction following, coding, and analysis
8 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V4 Flash 0731 (batch)deepseek/deepseek-v4-flash-0731:batch | DeepSeek |
1251.0 | 1.04858M | $0.11 | $0.33 | — | ||
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | DeepSeek |
1251.0 | 1M | $0.05 | $0.16 | 2026-07-31 | ||
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | DeepSeek |
1247.0 | 1M | $0.435 | $0.87 | 2026-04-24 | ||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | DeepSeek |
1220.0 | 1M | $0.15 | $0.6 | 2026-04-24 | ||
| DeepSeek Chatdeepseek/deepseek-chat | DeepSeek |
1132.0 | 1M | $0.147 | $0.295 | 2025-12-01 |