Skip to content
AI Atlas
ModelDeprecatedOpen weightsIdentity probable

Qwen3 VL 30B A3B Instruct

Qwenfamily · Qwen3

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...

Open in Graph
data quality60

Updated 6 h ago · first seen 11 Sept 2026

model_01M294WWAS1A069CEWSE9M3Z41

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
1
API aliases
qwen/qwen3-vl-30b-a3b-instructqwen3-vl-30b-a3b-instructqwen3-vl-30b-a3b-reasoningIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
1Effort / 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:Artificial AnalysisT2observed 5 d agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Architecture

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
imagetext
Input
imagetext
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    No

    Artificial Analysis · T2

  • Vision

    Yes

    OpenRouter public model & pricing listing · T2

  • 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 11 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 5 d agomedium

Benchmarks28

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 Analysisvarianthardreasoningoffconditions differ across rows → partially comparable4−59.8 ptvs gpt-5.6-solobs. 16 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · variant=Telecom · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantTelecomreasoningonconditions differ across rows → partially comparable2non-primary groupobs. 16 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−79.2 ptvs Z.ai GLM 5.2obs. 11 Sept 2026artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningonversion4.3conditions differ across rows → partially comparable4−43.9vs Claude Fable 5.1obs. 16 Sept 2026artificialanalysis.aiT2
IFBenchinstruction-following · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable4−38.2 ptvs Grok 4.3obs. 16 Sept 2026artificialanalysis.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable4−50.2 ptvs Claude Fable 5.1obs. 16 Sept 2026artificialanalysis.aiT2
MMMU-Promultimodal · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningoffconditions differ across rows → partially comparable4−24.7 ptvs gpt-6-astraobs. 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 Diamondreasoningonconditions differ across rows → partially comparable2−24.2 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. 28 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 & Pricing1

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MOutput / 1MStatusObservedSource
OpenRoutercheapest outputqwen/qwen3-vl-30b-a3b-instruct262.1Kout 16.4Kactive6 h agosince 16 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 1 provider

Output price history of Qwen3 VL 30B A3B Instruct$0$0.20$0.40$0.60$0.80Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.60 · 11 Sept 2026OpenRouter: $0.60 → $0.52 · 16 Sept 2026OpenRouter: $0.52 → $0.60 · 16 Sept 2026
  • OpenRouter
  • OpenRouter$0.52 → $0.6016 Sept 2026
  • OpenRouter$0.60 → $0.5216 Sept 2026
  • OpenRouterfirst observed $0.6011 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of Qwen3 VL 30B A3B Instruct$0$0.05$0.10$0.15$0.20Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.15 · 11 Sept 2026OpenRouter: $0.15 → $0.13 · 16 Sept 2026OpenRouter: $0.13 → $0.15 · 16 Sept 2026
  • OpenRouter
  • OpenRouter$0.13 → $0.1516 Sept 2026
  • OpenRouter$0.15 → $0.1316 Sept 2026
  • OpenRouterfirst observed $0.1511 Sept 2026

Versions & Artifacts0

Version history

Context window2 changes

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

Max output2 changes

11 Sept 2026→16 Sept 2026→16 Sept 2026current

Knowledge cutofffirst observation only

11 Sept 2026current

Opennessfirst observation only

11 Sept 2026current

Statusfirst 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.

Timeline20

Full timeline →

Change history42

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 →

Qwen3 VL 30B A3B Instruct 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.
42 claims · 24 properties

Release daterelease_date1

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

Statusstatus2

Claim history for Status
ValueValid from → toStatusSourceConfidenceExtractor
deprecated → currentcurrentArtificial AnalysisT2mediumdeterministic
deprecated → currentcurrentArtificial AnalysisT2mediumdeterministic

Opennessopenness2

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

Context windowcontext_length4

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
262.1K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic
256K tokens → supersededArtificial AnalysisT2mediumdeterministic
256K tokens → currentcurrentArtificial AnalysisT2mediumdeterministic
262.1K tokens → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Max outputmax_output_tokens3

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
16.4K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic
32.8K tokens → supersededOpenRouter public model & pricing listingT2mediumdeterministic
16.4K tokens → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Knowledge cutoffknowledge_cutoff1

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

Modalitiesmodalities1

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

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
image, 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
Qwen3 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
Qwen/Qwen3-VL-30B-A3B-Instruct → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Aa context windowaa_context_window1

Claim history for Aa context window
ValueValid from → toStatusSourceConfidenceExtractor
256,000 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
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception... → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Aa median output tokens per secondmetric.aa_median_output_tokens_per_second10

Claim history for Aa median output tokens per second
ValueValid from → toStatusSourceConfidenceExtractor
112.6 → currentcurrentArtificial AnalysisT2mediumdeterministic
112.5 → supersededArtificial AnalysisT2mediumdeterministic
112 → supersededArtificial AnalysisT2mediumdeterministic
111.8 → supersededArtificial AnalysisT2mediumdeterministic
111.6 → supersededArtificial AnalysisT2mediumdeterministic
111.8 → supersededArtificial AnalysisT2mediumdeterministic
111.6 → supersededArtificial AnalysisT2mediumdeterministic
110.7 → supersededArtificial AnalysisT2mediumdeterministic
113.1 → currentcurrentArtificial AnalysisT2mediumdeterministic
111.3 → supersededArtificial AnalysisT2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
qwen/qwen3-vl-30b-a3b-instruct → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter listed atopenrouter_listed_at1

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

Reasoningreasoning3

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentArtificial AnalysisT2mediumdeterministic
No → currentcurrentArtificial AnalysisT2mediumdeterministic
Yes → supersededArtificial AnalysisT2mediumdeterministic

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, logit_bias, logprobs, max_tokens, min_p, presence_penalty, 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

Visionvision1

Claim history for Vision
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

25

Source tiers

T225

Freshest observation

6 h ago

Conflicts

None

Source documents 2

Source documents
SourceDocumentTypeTierLast observedSnapshots
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary6 h ago72
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 (60/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →