DeepSeek V3.1
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...
DeepSeek V3.1 specs and pricing
- Provider: DeepSeek
- Released: August 21, 2025
- Context window: 164K tokens
- Max output: 147K tokens
- Input: text
- Output: text
- Price: $0.25 input / $0.95 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
FAQ
- How much does DeepSeek V3.1 cost? DeepSeek V3.1 costs $0.25 per million input tokens and $0.95 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.83 credits ($1 = 100 credits).
- What is the context window of DeepSeek V3.1? DeepSeek V3.1 can read up to 164K tokens at once and write up to 147K tokens in one reply.
- Can I use DeepSeek V3.1 without coding? Yes. In todo.is you pick DeepSeek V3.1 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.