October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
31 providers
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
Open MoE flagship with million-token context for coding and long agent runs
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017 | 1351.0 | 1M | $0.15 | $0.6 | 2026-10-17 | |||
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | 1254.0 | 1M | $0.66 | $1.98 | 2026-04-24 | |||
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | 1209.0 | 1M | $0.035 | $0.07 | 2026-07-31 | |||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | 1189.0 | 1M | $0.15 | $0.6 | 2026-04-24 | |||
| DeepSeek V3.2deepseek/deepseek-v3.2 | 1133.0 | 128K | $0.209 | $0.31 | 2025-12-01 |