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....
57 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
10 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | DeepSeek |
1228.0 | 1.04858M | $0.44 | $1.32 | 2026-07-31 | ||
| DeepSeek: DeepSeek V3.1deepseek/deepseek-chat-v3.1 | DeepSeek |
1110.0 | 163.84K | $0.25 | $0.95 | 2025-08-21 |