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

21–40 / 54

LMArena

1,404.988

source id
lmarena
leaderboard name
LMArena Text Polish
dimension
general
metric
Arena rating
rank
124
sample size
229
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1366.9020302368476
confidence upper
1443.0732085440986
Original result ↗

LMArena

1,382.46

source id
lmarena
leaderboard name
LMArena Text Industry Entertainment And Sports And Media
dimension
general
metric
Arena rating
rank
127
sample size
625
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1359.1847266214197
confidence upper
1405.7345892359936
Original result ↗

LMArena

1,417.22

source id
lmarena
leaderboard name
LMArena Text Overall
dimension
general
metric
Arena rating
rank
128
sample size
3605
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1407.4890819732295
confidence upper
1426.9504474370096
Original result ↗

LMArena

1,402.017

source id
lmarena
leaderboard name
LMArena Text Exclude Ties
dimension
general
metric
Arena rating
rank
133
sample size
2581
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1388.1723158472055
confidence upper
1415.8616899666981
Original result ↗

LMArena

1,404.107

source id
lmarena
leaderboard name
LMArena Text Style Control Non English
dimension
style
metric
Arena rating
rank
135
sample size
2025
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1391.3200344153468
confidence upper
1416.894474524566
Original result ↗

LMArena

1,418.665

source id
lmarena
leaderboard name
LMArena Text English
dimension
general
metric
Arena rating
rank
142
sample size
1580
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1404.1065910144634
confidence upper
1433.2231650279396
Original result ↗

LMArena

1,397.193

source id
lmarena
leaderboard name
LMArena Text Style Control Polish
dimension
style
metric
Arena rating
rank
144
sample size
229
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1359.2974305591003
confidence upper
1435.0893970231073
Original result ↗

LMArena

1,414.72

source id
lmarena
leaderboard name
LMArena Text Style Control Overall
dimension
style
metric
Arena rating
rank
145
sample size
3605
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1404.9972205488823
confidence upper
1424.4425881620195
Original result ↗

LMArena

1,419.023

source id
lmarena
leaderboard name
LMArena Text Style Control Longer Query
dimension
style
metric
Arena rating
rank
147
sample size
838
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1399.2882772954013
confidence upper
1438.758390905692
Original result ↗

LMArena

1,377.628

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Entertainment And Sports And Media
dimension
style
metric
Arena rating
rank
148
sample size
625
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1354.4255973880934
confidence upper
1400.830310759918
Original result ↗

LMArena

1,417.71

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Legal And Government
dimension
style
metric
Arena rating
rank
149
sample size
263
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1382.3314115339308
confidence upper
1453.0892432369176
Original result ↗

LMArena

1,407.527

source id
lmarena
leaderboard name
LMArena Text Industry Legal And Government
dimension
general
metric
Arena rating
rank
151
sample size
263
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1371.9379459714212
confidence upper
1443.1170203658507
Original result ↗

LMArena

1,400.131

source id
lmarena
leaderboard name
LMArena Text Style Control Exclude Ties
dimension
style
metric
Arena rating
rank
151
sample size
2581
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1386.181206010342
confidence upper
1414.0804821944632
Original result ↗

LMArena

1,401.838

source id
lmarena
leaderboard name
LMArena Text Math
dimension
general
metric
Arena rating
rank
158
sample size
216
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1363.3032636721784
confidence upper
1440.3721310357384
Original result ↗

LMArena

1,395.785

source id
lmarena
leaderboard name
LMArena Text Longer Query
dimension
general
metric
Arena rating
rank
158
sample size
838
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1376.0648379421996
confidence upper
1415.5042186918374
Original result ↗

LMArena

1,417.728

source id
lmarena
leaderboard name
LMArena Text Style Control English
dimension
style
metric
Arena rating
rank
159
sample size
1580
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1403.0530926181132
confidence upper
1432.4022497845067
Original result ↗

LMArena

1,424.075

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts
dimension
style
metric
Arena rating
rank
160
sample size
1898
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1410.8308658118435
confidence upper
1437.3184607400233
Original result ↗

LMArena

1,406.386

source id
lmarena
leaderboard name
LMArena Text Hard Prompts
dimension
general
metric
Arena rating
rank
160
sample size
1898
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1393.169319731735
confidence upper
1419.6031149623018
Original result ↗

LMArena

1,380.788

source id
lmarena
leaderboard name
LMArena Text Instruction Following
dimension
general
metric
Arena rating
rank
161
sample size
1016
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1362.9080816292824
confidence upper
1398.667972877924
Original result ↗

LMArena

1,394.121

source id
lmarena
leaderboard name
LMArena Text Style Control Instruction Following
dimension
style
metric
Arena rating
rank
164
sample size
1016
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1376.2755684513431
confidence upper
1411.9663035871154
Original result ↗

Published prices

1–6 / 6

Provider specifications & access

1–3 / 3

DeepSeek-V3.1-Terminus ↗

source model id
deepseek-ai/DeepSeek-V3.1-Terminus
hosting
siliconflow-hosted
platforms
  • SiliconFlow
max output tokens
163840
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling

deepseek-ai/DeepSeek-V3.1-Terminus ↗

source model id
publishers/deepseek-ai/models/deepseek-v3-1@deepseek-v3-1-terminus
hosting
vertex-self-deployed
platforms
  • Google Cloud Vertex AI
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    deepseek-ai/DeepSeek-V3.1-Terminus ↗

    source model id
    publishers/hf-deepseek-ai/models/deepseek-v3.1-terminus@001
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      Safety assessments

      1–1 / 1

      Foundation Model Transparency Index 2025 ↗

      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

      openRouter ↗

      field
      context_length
      value
      163840
      normalized value
      163840
      scope
      source-model
      source id
      openRouter
      confidence
      1

      siliconFlow ↗

      field
      context_length
      value
      164K
      scope
      source-model
      source id
      siliconFlow
      confidence
      1

      openRouter ↗

      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

      openRouter ↗

      field
      max_output_tokens
      value
      147456
      normalized value
      147456
      scope
      source-model
      source id
      openRouter
      confidence
      1

      siliconFlow ↗

      field
      max_output_tokens
      value
      164K
      scope
      source-model
      source id
      siliconFlow
      confidence
      1

      Original sources

      1–17 / 17

      DeepSeek · Model reference ↗

      SiliconFlow · Model page ↗

      Hugging Face · Model repository ↗

      DeepInfra · Model page ↗

      Google Cloud · Model page ↗

      Google Cloud · Model page ↗

      OpenRouter · Model page ↗

      SiliconFlow · Playground ↗

      SiliconFlow · API documentation ↗

      DeepInfra · Catalog ↗

      Epoch AI · Catalog ↗

      GitHub · Catalog ↗

      Google Cloud · Catalog ↗

      LMArena · Catalog ↗

      OpenRouter · Catalog ↗

      OpenRouter · Catalog ↗

      SiliconFlow · Catalog ↗

      Source links

      1–10 / 10

      Explore more models

      Models

      Loading
      EVIDENCE / COMPARISON

      Benchmarks

      Explore every benchmark

      Loading

      These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

      Install TensorTrace