DeepSeek V3.1 Terminus
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-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.
Input
Output
Context
164K
Max Output
8K
Parameters
671B
Technical Specifications
Model TypeChat
Context Window164K
Max Output Tokens8K
Parameters671B
Training Cutoff—
Licensemit
Capabilities
Input Modalities
text
Output Modalities
text
Features
code_generationfunction_callingjson_modereasoningstreamingtext_generation
Benchmarks
8.4%
HLE
75.1%
GPQA
32.1%
SciCode
83.6%
MMLU Pro
53.7
Math
31.9
Coding
52.9%
LiveCodeBench
28.5
Intelligence
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.