DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus is a text-based AI model developed by DeepSeek that focuses on improved language consistency and agent performance. Released in September 2025, it supports a large context window and includes native reasoning and tool-calling capabilities.
DeepSeek V3.1 Terminus specs and pricing
- Provider: DeepSeek
- Released: September 22, 2025
- Context window: 164K tokens
- Max output: 147K tokens
- Input: text
- Output: text
- Price: $0.27 input / $1.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What DeepSeek V3.1 Terminus is good at
- Complex reasoning tasks requiring logical consistency
- Automated agent workflows using external tools
- Processing large volumes of text data
To-dos to try with DeepSeek V3.1 Terminus
- Analyze a long technical document and summarize the key findings
- Use tool calling to retrieve specific data and format it into a report
- Solve a multi-step logical problem that requires step-by-step reasoning
FAQ
- What is the primary focus of the Terminus update? This version addresses user-reported issues regarding language consistency and enhances the model's agent capabilities.
- Does this model support multimodal inputs? No, DeepSeek V3.1 Terminus is limited to text-based inputs and outputs.
- How much does DeepSeek V3.1 Terminus cost? DeepSeek V3.1 Terminus costs $0.27 per million input tokens and $1.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.9 credits ($1 = 100 credits).
- What is the context window of DeepSeek V3.1 Terminus? DeepSeek V3.1 Terminus can read up to 164K tokens at once and write up to 147K tokens in one reply.
- Can I use DeepSeek V3.1 Terminus without coding? Yes. In todo.is you pick DeepSeek V3.1 Terminus 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.