Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for deepseek

DeepSeek: DeepSeek V3.1 Terminus

deepseek/deepseek-v3.1-terminus

Model weights
Compare

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. 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(opens in new tab)

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.

Modalities

In / Out Price

$0.27 / $1per 1M

Context

164K

Released

Sep 22, 2025

Knowledge Cutoff

Mar 2025

Compare

About DeepSeek: DeepSeek V3.1 Terminus

OpenRouter makes DeepSeek: DeepSeek V3.1 Terminus available through a unified, OpenAI-compatible API using the model ID deepseek/deepseek-v3.1-terminus. Requests can be routed across 4 providers, including SiliconFlow, NovitaAI, AtlasCloud and StreamLake, with automatic failover when an endpoint is unavailable.

DeepSeek: DeepSeek V3.1 Terminus accepts text and returns text. It has a 163,840-token context window and a maximum output of 163,840 tokens.

On OpenRouter, DeepSeek: DeepSeek V3.1 Terminus costs $0.27/M input tokens and $1.00/M output tokens. It was released on September 22, 2025; its knowledge cutoff is March 31, 2025.

More models from DeepSeek

  • DeepSeek V4 Pro 0813
  • DeepSeek V4 Flash 0731
  • DeepSeek V4 Pro 0423

Frequently asked questions

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes.

DeepSeek V3.1 Terminus costs $0.27/M input tokens and $1.00/M output tokens.

DeepSeek V3.1 Terminus has a 163,840 token context window. It supports up to 163,840 completion tokens.

Yes. DeepSeek V3.1 Terminus accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

DeepSeek V3.1 Terminus is served by 4 providers on OpenRouter: SiliconFlow, NovitaAI, AtlasCloud and StreamLake. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

DeepSeek V3.1 Terminus was released on September 22, 2025. Its knowledge cutoff is March 31, 2025.