← LLM Models→
DeepSeek V3.1
DeepSeek
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...
openrouter.ai ↗📖Context164K tokens
🚀Speed-
💵Input price$0.210/1M
💸Output price$0.790/1M
Made by
🏢
DeepSeek
providerMore from DeepSeek
API Providers
Details
- Provider
- DeepSeek
- Parameters
- -
- Context
- 164K tokens
- Speed
- -
- Open Source
- No
- License
- Proprietary
- Released
- Aug 2025

