How does DeepSeek V3.1 rank among AI models?
DeepSeek V3.1 is a superseded version and is not on the current board as of 6 November 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.
DeepSeek·#151 of 504 in the all-versions archive
DeepSeek V3.1 is a language model from DeepSeek. It ranks #151 of 504 in ModelCap's all-versions archive, with an Index score of 58.3, measured on 2 public benchmarks. Its score range of 53.3–63.3 spans positions #123–#184. It is listed at $0.25 per million input tokens and $0.95 per million output tokens across 4 providers. It reads up to 164K tokens of context, and its weights are openly downloadable.
Figures as of 6 Nov 2026, 13:52 UTC · download the public dataset · methodology
ModelCap Index · All-versions archive
58.3#151
Measured on 2 public benchmarks · range 53.3–63.3
Evidence as of 28 Oct 2026, 00:00 UTC
Superseded by DeepSeek V3.2. It no longer holds a current-board position; its all-versions archive rank is #151.
Input
$0.25
per 1M tokens
Output
$0.95
per 1M tokens
Context
164K
tokens
Providers
4
endpoints
Providers
Uptime measured over the last 30 minutesHugging Face Inference Providers
Exact repository identityProvider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.
Reasoning efforts
Best supported result can inform ModelCapPublished Max, X-High, High and other configurations for this model. These are sourced scores, not head-to-head essays.
Related community configurations
Human preference ratingReported evaluation leads (1)
Not independent measurementStructured 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.
Other versions (4)
ModelCap Index · All-versions archive
Methodology58.3
Measured on 2 public benchmarks
All-versions archive
#151 of 504
- Score range
- 53.3–63.3
- Rank range
- #123–#184
- Evidence as of
- 28 Oct 2026, 00:00 UTC
- Benchmarks used
- Arena Coding, Arena Overall
Technical details
- Public rank basis
- Measured (measured)
- Evidence label
- Measured · 2 public benchmark observations across 2 boards
- Index support
- 61.9% · strong
- Identity binding
- Exact catalogue product · deepseek/deepseek/deepseek-chat-v3.1/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata deepseek-ai/DeepSeek-V3.1@c0781d039fb7a1ba2abc4add0bdc293e92d2b8db (not the evaluation revision)
- Index observations used
- 2
- Qualified Index evidence point
- 58.3
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
- 58.3
- Evidence status
- confirmed · 77% mass
- General preference
- 58.8
- Coding
- 55.1
- Agents & tools
- —
- Reasoning
- —
- Evidence breadth
- 92%
- Evidence coverage
- 62%
Market and catalogue signals · secondary, never the language Index rank
- Usage (OpenRouter popularity)
- 21.0
- Liquidity (providers × uptime)
- 89.3
- Open reach (HF downloads)
- 92.0
- Surface (context / tools / modalities)
- 71.8
- Freshness
- 18.6
- · OpenRouter popularity #100
- · 4 live providers
- · HF 30d downloads 260033
- · Catalogue: context 163840, reasoning, tools
- · First seen 2025-08-21
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
- Arena Overall58.8
- Arena Coding · Thinking55.1
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 index87.8
strong · 98% metadata coverage
- Artifact reproducibility
- 100.0
- Access & legal clarity
- 100.0
- Deployability
- 92.0
- Evaluation provenance
- 51.2
Not yet published: pinned evaluation dataset versions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market activity
Venue coverage- Market Gravity
- 48.6
- OpenRouter weekly popularity
- #100 of 339
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
- #138 of 419
- Rating
- 1416.9
- 95% confidence interval
- 1411–1423
- Votes
- 15K
- Source published at
- 28 Oct 2026, 00:00 UTC
- Category
- overall
- Identity match confidence
- 100%
Market Gravity breakdown
- Usage55%
- 21.0
- Liquidity25%
- 89.3
- Open reach15%
- 92.0
- Freshness5%
- 18.6
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
Specification
- Model ID
deepseek/deepseek-chat-v3.1- Context window
- 164K tokens
- Declared output cap
- 147K tokens
OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata
- Inputs
- Text
- Outputs
- Text
- Tokenizer
- DeepSeek
- Cached input tokens
- $0.13 / 1M
- First seen on OpenRouter
- 21 Aug 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
- c0781d039fb7
- Parameters
- 684.5B
- Architecture
- DeepseekV3ForCausalLM
- Model type
- deepseek_v3
- Hugging Face downloads (30d)
- 260K
- Downloads (all time)
- 3.5M
- Likes
- 864
- Repository
- deepseek-ai/DeepSeek-V3.1
- Repository updated
- 5 Sept 2025, 11:30 UTC
- Base lineage
- deepseek-ai/DeepSeek-V3.1-Base
Benchmark leaderboards featuring DeepSeek V3.1
All leaderboardsDeepSeek V3.1: common questions
How much does DeepSeek V3.1 cost per 1M tokens?
DeepSeek V3.1 is listed at $0.25 per 1M input tokens and $0.95 per 1M output tokens as of 6 November 2026 across 4 providers. 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 $0.975 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?
DeepSeek V3.1 has a published context window of 164K tokens (163,840). The snapshot lists a 147,456 token catalogue-declared route output cap. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. The providers table lists each endpoint's context limit.
Is DeepSeek V3.1 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 on Hugging Face.
Which API providers serve DeepSeek V3.1?
4 providers serve DeepSeek V3.1 through OpenRouter as of 6 November 2026: DeepInfra, SiliconFlow, CoreWeave and SambaNova. Each provider's price, context limit, quantization and measured uptime are in the providers table above.
Which benchmarks has DeepSeek V3.1 been evaluated on?
DeepSeek V3.1 has published results on 2 public boards tracked by ModelCap as of 6 November 2026: Arena text 1417 (#138 of 419) and Arena coding 1455 (#152 of 414). Each board page ranks every tracked model on that benchmark. The ModelCap Index scores the results its methodology admits, with published uncertainty, and shows reference boards without scoring them.
When was DeepSeek V3.1 released?
DeepSeek V3.1 first appeared in the catalogue on 21 Aug 2025, with a published knowledge cutoff of 2025-03-31. It has since been superseded by DeepSeek V3.2. Rank and price movements since then are recorded on the site's changes feed.