Loading...
Loading...
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 training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.
Price/1M
$0.30
329th cheapest
3% below median
Top 50%
Context Window
33K
291st largest
Top 91%
Input
$0.15
per 1M tokens
Output
$0.75
per 1M tokens
Blended
$0.30
per 1M tokens
Cheaper than 50% of models. Median price is $0.31/1M tokens.
Daily
$0.30
Monthly
$9.00
Context Window
33K
tokens
Larger than 9% of models
Max Output
7K
tokens
22% of context
Context Window Comparison