Skip to content
ModelCap

DeepSeek V3.1 Terminus

Current board #69Arena #127Official publisher releaseOpen weights

DeepSeek·deepseek/deepseek-v3.1-terminus

DeepSeek V3.1 Terminus is ModelCap current-board rank #69 with Index 58.9 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.

DeepSeek V3.1 Terminus listed OpenRouter input price is $0.27 per 1M tokens and listed output price is $1.00 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.

DeepSeek V3.1 Terminus has a published context limit of 164K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.

DeepSeek V3.1 Terminus has 4 published OpenRouter serving endpoints, from OpenRouter as of 22 Sept 2026, 02:49 UTC.

DeepSeek V3.1 Terminus weight access is open weights, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
58.9#69
Measured · 68% support · score interval 50.9–66.9
Evidence as of 19 Sept 2026, 22:46 UTC
Market Gravity
28.2Decreased by 0.1
Secondary market signal
Input
$0.27
per 1M tokens
Output
$1.00
per 1M tokens
Context
164K
tokens
Providers
4
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
AtlasCloudfp8Cheapest$0.30$0.95131Kfp8100.0%
SiliconFlowfp8$0.27$1.00164Kfp899.66%
Novitafp8$0.27$1.00131Kfp8100.0%
StreamLake$0.343$1.03128K100.0%

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
deepinfra
live
$0.27$0.95164K609 ms25.9 tok/stools · structured
novita
live
$0.27$1.00131K1450 ms36.2 tok/stools · structured
featherless-ai
live

Reasoning efforts

Best supported result can inform ModelCap

Published Max, X-High, High and other configurations for this model. These are sourced scores, not head-to-head essays.

Related community configurations

Human preference rating
ConfigurationRatingSource rankVotesSource
Thinking
deepseek-v3.1-terminus-thinking
1417
CI 1407–1428
#1223KLMArena
Match 100%

Reported evaluation leads (1)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
Idavidrein/gpqa
diamond
74.2424
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
58.9
Measured · 3 public benchmark observations across 3 boards
Current board
#69
Public rank basis
Measured (measured)
Index support
67.7% · strong
Index interval
50.9–66.9
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
19 Sept 2026, 22:46 UTC
Identity binding
Exact catalogue product · deepseek/deepseek/deepseek-v3.1-terminus/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata deepseek-ai/DeepSeek-V3.1-Terminus@19510d6dc61f79dbd925bd51ee8a9081c509a4b6 (not the evaluation revision)
Index observations used
3
Qualified Index evidence point
58.9
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
58.9
Evidence status
confirmed · 78% mass
General preference
59.2
Coding
56.8
Agents & tools
Reasoning
Evidence breadth
92%
Evidence coverage
68%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
12.5
Liquidity (providers × uptime)
66.2
Open reach (HF downloads)
23.6
Surface (context / tools / modalities)
71.8
Freshness
24.9
  • · OpenRouter popularity #156
  • · 4 live providers
  • · HF 30d downloads 22532
  • · Catalogue: context 163840, reasoning, tools
  • · First seen 2025-09-22

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
92.6
strong · 98% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
97.5
Evaluation provenance
66.7

Missing: evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
28.2
OpenRouter weekly popularity
#156 of 322

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
LMArena
Official rank
#127 of 402
Rating
1414.7
95% confidence interval
1405–1424
Votes
4K
Source published at
13 Sept 2026, 00:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
12.5

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
66.2

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
23.6

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
24.9

Time since first public availability, on a six-month half-life.

Specification

Context window
164K tokens
Max output
33K tokens
Inputs
Text
Outputs
Text
Tokenizer
DeepSeek
Cached input tokens
$0.135 / 1M
First seen on OpenRouter
22 Sept 2025
Knowledge cutoff
2025-03-31

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
mit
Pinned revision
19510d6dc61f
Parameters
684.5B
Architecture
DeepseekV3ForCausalLM
Model type
deepseek_v3
Hugging Face downloads (30d)
23K
Downloads (all time)
255K
Likes
368
Repository updated
29 Sept 2025, 01:52 UTC

Compare DeepSeek V3.1 Terminus with

Pick any model

Benchmark leaderboards featuring DeepSeek V3.1 Terminus

All leaderboards
Public benchmark boards on which DeepSeek V3.1 Terminus has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena coding leaderboardArena (LMArena)14611438–1485#123 of 397Thinking13 Sept 2026
Artificial Analysis Intelligence IndexArtificial Analysis14.8#117 of 151intelligence-index:v4.3:reasoning-unspecified19 Sept 2026
τ²-Bench Telecom (Artificial Analysis run)Artificial Analysis37.1%#239 of 436tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="DeepSeek V3.1 Terminus (Non-reasoning)":reasoning=false5 Sept 2026
Humanity's Last Exam (Artificial Analysis run)Artificial Analysis8.7%#316 of 615hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="DeepSeek V3.1 Terminus (Non-reasoning)":reasoning=false5 Sept 2026

Alternatives to DeepSeek V3.1 Terminus, by the numbers

Ranked neighbours

Models within 3 places of #69 on the ModelCap Index.

Cheaper at a similar or higher Index

Index score within 3 points of, or above, this model's, with a lower listed blended price (3:1 input:output).

Other ranked DeepSeek models

The same publisher's other current models with a public Index position.

DeepSeek V3.1 Terminus: common questions

How does DeepSeek V3.1 Terminus rank among AI models?

DeepSeek V3.1 Terminus holds ModelCap Index position #69 of 248 ranked language models as of 22 September 2026, with an Index score of 58.9 (interval 50.9–66.9); evidence: measured. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does DeepSeek V3.1 Terminus cost per 1M tokens?

DeepSeek V3.1 Terminus is listed at $0.27 per 1M input tokens and $1.00 per 1M output tokens as of 22 September 2026; the lowest output price among 4 providers is $0.95 on AtlasCloud. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $1.04 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of DeepSeek V3.1 Terminus?

DeepSeek V3.1 Terminus has a published context window of 164K tokens (163,840) and a maximum output of 33K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.

Is DeepSeek V3.1 Terminus open-weight?

Open weights (mit). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is deepseek-ai/DeepSeek-V3.1-Terminus on Hugging Face.

Which API providers serve DeepSeek V3.1 Terminus?

4 providers serve DeepSeek V3.1 Terminus through OpenRouter as of 22 September 2026: SiliconFlow, Novita, AtlasCloud and StreamLake. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

Which benchmarks has DeepSeek V3.1 Terminus been evaluated on?

DeepSeek V3.1 Terminus has published results on 4 public boards tracked by ModelCap as of 22 September 2026: Arena coding 1461 (#123 of 397), AA Intelligence Index 14.8 (#117 of 151), AA τ²-Bench Telecom 37.1% (#239 of 436) and AA Humanity's Last Exam 8.7% (#316 of 615). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

How does DeepSeek V3.1 Terminus compare with Dots3-Note Preview?

DeepSeek V3.1 Terminus ranks #69 (Index 58.9) and Dots3-Note Preview ranks #68 (Index 59.3) on the ModelCap Index as of 22 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was DeepSeek V3.1 Terminus released?

DeepSeek V3.1 Terminus first appeared in the catalogue on 22 Sept 2025, with a published knowledge cutoff of 2025-03-31. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.