Skip to content
AI Atlas
ModelAnnouncedOpen weightsIdentity probable

DeepSeek V3.2 Exp

DeepSeekfamily · DeepSeek

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Open in Graph
data quality67

Updated 4 d ago · first seen 11 Sept 2026

model_01M294WWB78928015NA9WBEVMF

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
2
API aliases
deepseek-v3-2-reasoning-0925deepseek/deepseek-v3.2-expIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Open weights— weights downloadable; 7 dimensions unknown.

Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    —

  • Redistribution

    —

  • Derivatives

    —

dimensions marked null are unknown, not false

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Status

Source:DeepSeek — site & API docsT2observed 5 d agomediumLLM-extracted

Version

Source:DeepSeek — site & API docsT2observed 5 d agomediumLLM-extracted

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Paper
github.com/deepseek-ai/DeepSeek-V3.2-Exp/blob/main/DeepSeek_V3_2.pdf

Source:DeepSeek — site & API docsT2observed 5 d agomediumLLM-extracted

Repository
huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp

Source:DeepSeek — site & API docsT2observed 5 d agomediumLLM-extracted

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Architecture

Architecture

Source:DeepSeek — site & API docsT2observed 5 d agomediumLLM-extracted

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Benchmarks18

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
Terminal-Benchagentic · accuracy · variant=hard · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvarianthardreasoningonconditions differ across rows → partially comparable3−34.8 ptvs gpt-5.6-solobs. 16 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · variant=Telecom · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantTelecomreasoningoffconditions differ across rows → partially comparable2non-primary groupobs. 16 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysis1−65.2 ptvs Z.ai GLM 5.2obs. 11 Sept 2026artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningonversion4.3conditions differ across rows → partially comparable3−36.8vs Claude Fable 5.1obs. 16 Sept 2026artificialanalysis.aiT2
IFBenchinstruction-following · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable3−29.2 ptvs Grok 4.3obs. 16 Sept 2026artificialanalysis.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable3−44.3 ptvs Claude Fable 5.1obs. 16 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantDiamondreasoningonconditions differ across rows → partially comparable2non-primary groupobs. 16 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamond1−16.6 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 18 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing2

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MOutput / 1MStatusObservedSource
DeepSeek APIcheapest outputdeepseek/deepseek-v3.2-exp163.8Kout 65.5Kactive5 d agosince 11 Sept 2026openrouter.aiT2
OpenRouterdeepseek/deepseek-v3.2-exp163.8Kout 65.5Kactive3 h agosince 12 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 2 providers

Output price history of DeepSeek V3.2 Exp$0$0.10$0.20$0.30$0.40$0.50Sept 26Sept 26Sept 26Sept 26Sept 26DeepSeek API: first observed → $0.41 · 11 Sept 2026OpenRouter: first observed → $0.41 · 12 Sept 2026
  • DeepSeek API
  • OpenRouter
  • OpenRouterfirst observed $0.4112 Sept 2026
  • DeepSeek APIfirst observed $0.4111 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of DeepSeek V3.2 Exp$0$0.10$0.20$0.30$0.40Sept 26Sept 26Sept 26Sept 26Sept 26DeepSeek API: first observed → $0.27 · 11 Sept 2026OpenRouter: first observed → $0.27 · 12 Sept 2026
  • DeepSeek API
  • OpenRouter
  • OpenRouterfirst observed $0.2712 Sept 2026
  • DeepSeek APIfirst observed $0.2711 Sept 2026

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
ANCESTORS 1V3.1-TerminusV3.1-TerminusDeepSeek V3.2 Expthis modelDeepSeek V3.2 Exp — this model

Versions & Artifacts0

Version history

Context window2 changes

11 Sept 2026→11 Sept 2026→12 Sept 2026current

Openness1 change

11 Sept 2026→11 Sept 2026

Status1 change

11 Sept 2026→11 Sept 2026

Knowledge cutofffirst observation only

11 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline14

Full timeline →

Change history34

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 16 Mar 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

DeepSeek V3.2 Exp was not yet in AI Atlas on 16 Mar 2026

First seen 11 Sept 2026. Nothing is inferred backwards: no attribute is shown for dates before the first observation.
34 claims · 29 properties

Familyfamily1

Claim history for Family
ValueValid from → toStatusSourceConfidenceExtractor
DeepSeek-V3 → currentcurrentDeepSeek — site & API docsT2mediumllm

Versionversion1

Claim history for Version
ValueValid from → toStatusSourceConfidenceExtractor
3.2-Exp → currentcurrentDeepSeek — site & API docsT2mediumllm

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
29 Sept 2025 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Statusstatus2

Claim history for Status
ValueValid from → toStatusSourceConfidenceExtractor
deprecated → supersededArtificial AnalysisT2mediumdeterministic
announced → currentcurrentDeepSeek — site & API docsT2mediumllm

Opennessopenness3

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weights → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived
open-weights → supersededArtificial AnalysisT2mediumdeterministic
open-source → supersededDeepSeek — site & API docsT2mediumllm

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
transformer decoder with DeepSeek Sparse Attention (DSA) → currentcurrentDeepSeek — site & API docsT2mediumllm

Context windowcontext_length3

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
163.8K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic
128K tokens → supersededArtificial AnalysisT2mediumdeterministic
163.8K tokens → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
65.5K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Knowledge cutoffknowledge_cutoff1

Claim history for Knowledge cutoff
ValueValid from → toStatusSourceConfidenceExtractor
Jul 2025 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tokenizertokenizer1

Claim history for Tokenizer
ValueValid from → toStatusSourceConfidenceExtractor
DeepSeek → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
deepseek-ai/DeepSeek-V3.2-Exp → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Paperpaper_url1

Claim history for Paper
ValueValid from → toStatusSourceConfidenceExtractor
https://github.com/deepseek-ai/DeepSeek-V3.2-Exp/blob/main/DeepSeek_V3_2.pdf → currentcurrentDeepSeek — site & API docsT2mediumllm

Repositoryrepository_url1

Claim history for Repository
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp → currentcurrentDeepSeek — site & API docsT2mediumllm

Aa context windowaa_context_window1

Claim history for Aa context window
ValueValid from → toStatusSourceConfidenceExtractor
128,000 tokens → currentcurrentArtificial AnalysisT2mediumdeterministic

Aa deprecatedaa_deprecated1

Claim history for Aa deprecated
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentArtificial AnalysisT2mediumdeterministic

Aa opennessaa_openness1

Claim history for Aa openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weights → currentcurrentArtificial AnalysisT2mediumdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism... → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Hardware requirementshardware_requirements1

Claim history for Hardware requirements
ValueValid from → toStatusSourceConfidenceExtractor
Key GPU kernels in TileLang & CUDA → currentcurrentDeepSeek — site & API docsT2mediumllm

Instruct typeinstruct_type1

Claim history for Instruct type
ValueValid from → toStatusSourceConfidenceExtractor
deepseek-v3.1 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
deepseek/deepseek-v3.2-exp → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter listed atopenrouter_listed_at1

Claim history for Openrouter listed at
ValueValid from → toStatusSourceConfidenceExtractor
29 Sept 2025 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Reasoningreasoning1

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Weights availableweights_available1

Claim history for Weights available
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

29

Source tiers

T229

Freshest observation

4 d ago

Conflicts

None

Source documents 3

Source documents
SourceDocumentTypeTierLast observedSnapshots
DeepSeek — site & API docsapi-docs.deepseek.com/news/news250929 newsT1· Official5 d ago1
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary3 h ago74
Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary6 h ago17

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (67/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →