DeepSeek: 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 con…
deepseek/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. 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](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)
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.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 163840
- Knowledge cutoff
- 2025-03-31
- Published model ID
- DeepSeek-V3.1-Terminus
- Capabilities
- reasoning, structuredOutputs, toolCalling
Description source ↗Evaluations
41–54 / 54
1,387.288
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Business And Management And Financial Operations
- dimension
- general
- metric
- Arena rating
- rank
- 164
- sample size
- 717
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1365.4593558042372
- confidence upper
- 1409.1159273622989
Original result ↗1,406.751
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts English
- dimension
- general
- metric
- Arena rating
- rank
- 165
- sample size
- 848
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1387.0304636114058
- confidence upper
- 1426.4713352720864
Original result ↗1,410.087
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 170
- sample size
- 1277
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1393.943776484033
- confidence upper
- 1426.230149623312
Original result ↗1,407.446
- source id
- lmarena
- leaderboard name
- LMArena Text Coding
- dimension
- general
- metric
- Arena rating
- rank
- 170
- sample size
- 769
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1386.8936050230525
- confidence upper
- 1427.9991295319198
Original result ↗1,396.407
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Math
- dimension
- style
- metric
- Arena rating
- rank
- 170
- sample size
- 216
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1357.459337637972
- confidence upper
- 1435.3542485860653
Original result ↗1,440.168
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Coding
- dimension
- style
- metric
- Arena rating
- rank
- 173
- sample size
- 769
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1419.549240475149
- confidence upper
- 1460.7867994983299
Original result ↗1,424.437
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts English
- dimension
- style
- metric
- Arena rating
- rank
- 173
- sample size
- 848
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1404.6488642111024
- confidence upper
- 1444.225408671755
Original result ↗1,396.595
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Business And Management And Financial Operations
- dimension
- style
- metric
- Arena rating
- rank
- 173
- sample size
- 717
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1374.8958697542532
- confidence upper
- 1418.2947935582872
Original result ↗1,387.776
- source id
- lmarena
- leaderboard name
- LMArena Text Multi Turn
- dimension
- general
- metric
- Arena rating
- rank
- 174
- sample size
- 658
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1365.1795001910834
- confidence upper
- 1410.3720025219131
Original result ↗1,428.458
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Software And It Services
- dimension
- style
- metric
- Arena rating
- rank
- 175
- sample size
- 1277
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1412.3236635510675
- confidence upper
- 1444.591478896373
Original result ↗1,394.169
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Multi Turn
- dimension
- style
- metric
- Arena rating
- rank
- 178
- sample size
- 658
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.1-Terminus
- confidence lower
- 1371.570190498303
- confidence upper
- 1416.7672016329293
Original result ↗43.5
- source id
- artificialAnalysis
- dimension
- coding
- metric
- Coding Index
Original result ↗14.8
- source id
- artificialAnalysis
- dimension
- intelligence
- metric
- Intelligence Index
Original result ↗6.8
- source id
- artificialAnalysis
- dimension
- agentic
- metric
- Agentic Index
Original result ↗Published prices
1–6 / 6
$0.27
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$0.95
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.27
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$1.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.27
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- Input tokens (per 1M)
$1.00
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- Output tokens (per 1M)
Provider specifications & access
1–3 / 3
- source model id
- deepseek-ai/DeepSeek-V3.1-Terminus
- hosting
- siliconflow-hosted
- max output tokens
- 163840
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- source model id
- publishers/deepseek-ai/models/deepseek-v3-1@deepseek-v3-1-terminus
- hosting
- vertex-self-deployed
- source model id
- publishers/hf-deepseek-ai/models/deepseek-v3.1-terminus@001
- hosting
- vertex-self-deployed
Safety assessments
1–1 / 1
32 / 100
- source id
- stanfordFMTI
- canonical model id
- deepseek/deepseek-v3.1-terminus
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- DeepSeek
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 32 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–5 / 5
- field
- context_length
- value
- 163840
- normalized value
- 163840
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 164K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-03-31
- normalized value
- 2025-03-31
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 147456
- normalized value
- 147456
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 164K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
Explore more models