by ·
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.
| Signal | Strength | Weight | Impact |
|---|---|---|---|
| Benchmarksjust now | 69 | 30% | +20.8 |
| Recencyjust now | 93 | 15% | +13.9 |
| Capabilitiesjust now | 67 | 20% | +13.3 |
| Context Windowjust now | 72 | 10% | +7.2 |
| Output Capacityjust now | 64 | 10% | +6.4 |
| Pricingjust now | 1 | 15% | +0.1 |
View this model against the provider’s recent shipping cadence.
Community and practitioner feedback adds real-world signal on top of benchmarks and pricing.
Share your experience with DeepSeek V3.1 and help the community make better decisions.
Pricing, benchmarks, and reliability come from different data surfaces, so they refresh on different cadences. The timestamps above show the latest verification point we have for each one.
Cost Estimator
You save $37.90/month vs category average
From verified sources.