Open MoE flagship with million-token context for coding and long agent runs
62 providers
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
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
DeepSeek chat model for instruction following, coding, and analysis
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | 1283.0 | 1M | $0.435 | $0.87 | 2026-04-24 | |||
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | 1238.0 | 1M | $0.035 | $0.07 | 2026-07-31 | |||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | 1217.0 | 1M | $0.15 | $0.6 | 2026-04-24 | |||
| DeepSeek Chatdeepseek/deepseek-chat | 1115.0 | 1M | $0.147 | $0.295 | 2025-12-01 |