DeepSeek-V3.1-Terminus. The latest update builds on V3.1's strengths while addressing key user feedback. Language consistency improvements (fewer CN/EN mix-ups, no random chars), stronger Code Agent & Search Agent performance, and more stable, reliable outputs across benchmarks. FP8.
Added Aug 2, 2025
Model weightsContext Window
128.0K
Max Output
65.5K
Avg output tokens (7d)
704 tokens
Input Price (Auto)
$0.21/1M
Output Price (Auto)
$0.79/1M
Cache Read (Auto)
$0.11/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
21.7
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
75.1%
Better than 59% of models compared
HLE
Humanity's Last Exam
8.7%
Better than 53% of models compared
IFBench
Instruction-following benchmark
41.2%
Better than 41% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
37.1%
Better than 45% of models compared
AA-LCR
Long context reasoning evaluation
45.0%
Better than 50% of models compared
Coding
SciCode
Python programming for scientific computing
32.1%
Better than 45% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
31.8%
Better than 75% of models compared
LiveCodeBench
Contamination-free coding benchmark
52.9%
Better than 60% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
53.7%
Better than 50% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
83.6%
Better than 85% of models compared
Last updated Aug 16, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare DeepSeek V3.1 Terminus with similar models from the same provider or model family.
DeepSeek V3.1 Terminus (Thinking)
deepseek-ai/DeepSeek-V3.1-Terminus:thinkingThinking-enabled DeepSeek-V3.1-Terminus with improved language consistency, upgraded Code/Search Agents, and stronger stability and reliability versus V3.1. FP8.
DeepSeek V3.1
deepseek-ai/DeepSeek-V3.1DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. It does better at tool calling and agent tasks, and has higher thinking efficiency than its predecessor. This is the non-thinking version. Quantized at FP8.
DeepSeek R1 0528
deepseek-ai/DeepSeek-R1-0528The new (May 28th) Deepseek R1 model.
DeepSeek V3.1 Thinking
deepseek-ai/DeepSeek-V3.1:thinkingThinking enabled version of Deepseek V3.1. DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. It does better at tool calling and agent tasks, and has higher thinking efficiency than its predecessor. Quantized at FP8.
DeepSeek V3.2 Exp
deepseek-ai/deepseek-v3.2-expDeepseek V3.2 Exp, Deepseek's latest model offering far better performance especially on longer contexts than its predecessors. Current flagship model by Deepseek. FP8.
DeepSeek V3.2 Exp Thinking
deepseek-ai/deepseek-v3.2-exp-thinkingDeepseek V3.2 Exp Thinking, Deepseek's latest model offering far better performance especially on longer contexts than its predecessors. Current flagship model by Deepseek. FP8.