DeepSeek V3.1 Terminus (Thinking)
Thinking-enabled DeepSeek-V3.1-Terminus with improved language consistency, upgraded Code/Search Agents, and stronger stability and reliability versus V3.1. FP8.
- Tool Calling
- Structured Output
Pricing
Auto routing · per 1M tokens- Input
- $0.25
- Output
- $0.70
- Cache read
- $0.125
Specifications
- Context window
- 128K
- Max output
- 65.5K
- Parameters
- 671B / 37B
- Total / active
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1416.0
Overall Rank
#141 / 421
Votes
3,361
Confidence Interval
1405.8 - 1426.1
Category Scores
Coding
#147 / 416
627 votes
1459.1
Longer Query
#102 / 399
675 votes
1444.4
Creative Writing
#141 / 419
435 votes
1384.9
Instruction Following
#119 / 421
851 votes
1417.9
Hard Prompts
#129 / 421
1,649 votes
1444.8
Additional Categories14
Industry Legal And Government
#77 / 393
258 votes
1461.6
Industry Medicine And Healthcare
#87 / 390
224 votes
1464.8
Industry Writing And Literature And Language
#110 / 420
758 votes
1408.5
Russian
#112 / 385
282 votes
1428.9
Polish
#115 / 244
207 votes
1419.9
Industry Life And Physical And Social Science
#128 / 419
528 votes
1442.4
Industry Business And Management And Financial Operations
#129 / 414
691 votes
1421.1
Hard Prompts English
#135 / 419
724 votes
1446.8
Industry Entertainment And Sports And Media
#136 / 419
608 votes
1387.2
Non English
#139 / 421
1,906 votes
1402.5
Multi Turn
#144 / 419
573 votes
1415.3
Exclude Ties
#148 / 421
2,418 votes
1401.1
English
#149 / 421
1,455 votes
1424.6
Industry Software And It Services
#154 / 421
1,126 votes
1444.7
Published 2026-11-09 · Matched as DeepSeek-V3.1-Terminus (Thinking) · CC BY 4.0
LMArena DatasetLeaderboard results
These leaderboards tested DeepSeek V3.1 Terminus, another version of this model.
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 57.6 | #14 of 149 |
UGI Willingness | 6.0 | #26 of 149 |
UGI Writing | 54.0 | #51 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
 | $0.25 | $0.70 | $0.125 | N/A | N/A |
| $0.284 | $1.05 | N/A | N/A | N/A |
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.