DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
30 providers
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
Classic open reasoning model for transparent math, coding, and deliberate problem solving
Open DeepSeek MoE chat model for coding, math, and general reasoning
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813 | 1M | $0.442 | $0.884 | 2026-08-12 | |||
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | 1M | $0.035 | $0.07 | 2026-07-31 | |||
| DeepSeek-R1deepseek/deepseek-r1 | 128K | $0.7 | $2.5 | 2025-01-20 | |||
| DeepSeek-V3deepseek/deepseek-v3 | 131.072K | $0.27 | $1.12 | 2024-12-26 |