Open MoE flagship with million-token context for coding and long agent runs
62 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
62 providers
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
43 providers
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....
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
24 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | DeepSeek |
1170.0 | 1M | $0.435 | $0.87 | 2026-04-24 | ||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | DeepSeek |
1131.0 | 1M | $0.15 | $0.6 | 2026-04-24 | ||
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | DeepSeek |
1116.0 | 1M | $0.035 | $0.07 | 2026-07-31 | ||
| DeepSeek: DeepSeek V4 Flash 0731 (batch)deepseek/deepseek-v4-flash-0731:batch | DeepSeek |
1116.0 | 1.04858M | $0.11 | $0.33 | — | ||
| DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek |
1102.0 | 128K | $0.18 | $0.35 | 2025-12-01 |