DeepSeek V3.1 Terminus
by DeepSeektext->text2 endpoints
Neura Intelligence Index
43.9/ 100
Rank
#215—
Confidence
mediumBenchmarks
7(18% coverage)
Overview
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...
Capabilities
Text generation
Tool use / Function calling
Structured output
Extended reasoning
Long context
Top-P sampling
Stop sequences
Modalities
Input
Text
Output
Text
Technical Specifications
Context Window
163.8K tokens
Max Output
147.5K tokens
Knowledge Cutoff
2025-03-31
Tokenizer
DeepSeek
Uptime (24h)
10000.0%
Parameters
671000000000B
License
mitOpen Weights
Country
🇨🇳CN
Release Date
January 10, 20251y
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Benchmark Performance
general
| Benchmark | Score | Source |
|---|---|---|
| SimpleQA | 93.4 | verified |
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Verified | 66 | verified |
| TerminalBench | 31.3 | verified |
math
| Benchmark | Score | Source |
|---|---|---|
| AIME 2025 | 49.8 | verified |
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 74.9 | verified |
| Humanity's Last Exam | 15.9 | verified |
agent
| Benchmark | Score | Source |
|---|---|---|
| BrowseComp | 30 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.27
Output$1.00
Added
September 22, 2025
Last synced 10/23/2026