Skip to content
ModelCap

Qwen3 VL 30B A3B Instruct

Official publisher releaseOpen weights

Qwen·qwen/qwen3-vl-30b-a3b-instruct

Qwen3 VL 30B A3B Instruct listed OpenRouter input price is $0.13 per 1M tokens and listed output price is $0.52 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.

Qwen3 VL 30B A3B Instruct has a published context limit of 262K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.

Qwen3 VL 30B A3B Instruct has 4 published OpenRouter serving endpoints, from OpenRouter as of 22 Sept 2026, 02:49 UTC.

Qwen3 VL 30B A3B Instruct 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
Not scored · 0% support · score interval not available
Market Gravity
34.5Decreased by 0.2
Secondary market signal
Input
$0.13
per 1M tokens
Output
$0.52
per 1M tokens
Context
262K
tokens
Providers
4
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
AlibabaCheapest$0.13$0.52131K99.88%
DeepInfrafp8$0.15$0.60262Kfp891.61%
Novitabf16$0.20$0.70131Kbf1698.96%
SiliconFlowfp8$0.29$1.00262Kfp899.58%

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
$0.15$0.60262K306 ms34.4 tok/stools · structured
novita
live
$0.20$0.70131K580 ms118.4 tok/stools · structured
featherless-ai
live

ModelCap Index · Current board

Methodology
Not scored · peers unresolved
Public rank basis
Not scored (abstained)
Index support
0.0% · not applicable
Index interval
Not available
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
No admitted evaluation publication timestamp
Identity binding
Exact catalogue product · qwen/qwen/qwen3-vl-30b-a3b-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata Qwen/Qwen3-VL-30B-A3B-Instruct@9c4b90e1e4ba969fd3b5378b57d966d725f1b86c (not the evaluation revision)
Index observations used
0
Architecture fallback
abstained · 0% coverage · 0 anchors
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
Evidence status
No admitted measured evidence
General preference
Coding
Agents & tools
Reasoning
Evidence breadth
0%
Evidence coverage
0%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
11.9
Liquidity (providers × uptime)
65.6
Open reach (HF downloads)
68.2
Surface (context / tools / modalities)
65.3
Freshness
26.4
  • · OpenRouter popularity #162
  • · 4 live providers
  • · HF 30d downloads 476406
  • · Catalogue: context 262144, tools, modalities Text/Image
  • · First seen 2025-10-06

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

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.

Experimental capability estimate

Estimate policy
34.1
17.9–50.3 uncertainty interval
Excluded from rank
Confidence
75%
Training support
209 models · 120 lineages
Out-of-domain check
in domain
Feature coverage
100%
Lineage-held-out error
10.0 MAE

Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.

Deployment readiness

Metadata index
74.5
partial · 76% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
96.5
Evaluation provenance
0.0

Missing: artifactReproducibility.base-lineage, evaluationProvenance.admitted-evaluation-observations, evaluationProvenance.capability-family-breadth, evaluationProvenance.evaluation-source-diversity, evaluationProvenance.identity-and-source-confidence, 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
34.5
OpenRouter weekly popularity
#162 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

No matched Arena rating

This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.

Market Gravity breakdown

Usage55%
11.9

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
65.6

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

Open reach15%
68.2

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

Freshness5%
26.4

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

Specification

Context window
262K tokens
Max output
33K tokens
Inputs
Text, Image
Outputs
Text
Tokenizer
Qwen3
Cached input tokens
Not offered
First seen on OpenRouter
6 Oct 2025
Knowledge cutoff
2025-03-31

Capabilities

  • Not 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
apache-2.0
Pinned revision
9c4b90e1e4ba
Parameters
31.1B
Architecture
Qwen3VLMoeForConditionalGeneration
Model type
qwen3_vl_moe
Hugging Face downloads (30d)
476K
Downloads (all time)
17.9M
Likes
602
Repository updated
26 Nov 2025, 13:18 UTC

Benchmark leaderboards featuring Qwen3 VL 30B A3B Instruct

All leaderboards
Public benchmark boards on which Qwen3 VL 30B A3B Instruct has a published result
LeaderboardScoreSource rankConfigurationPublished
τ²-Bench Telecom (Artificial Analysis run)Artificial Analysis19.0%#360 of 436tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Qwen3 VL 30B A3B Instruct":reasoning=false13 Sept 2026
Humanity's Last Exam (Artificial Analysis run)Artificial Analysis6.3%#370 of 615hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Qwen3 VL 30B A3B Instruct":reasoning=false13 Sept 2026

Qwen3 VL 30B A3B Instruct: common questions

How does Qwen3 VL 30B A3B Instruct rank among AI models?

Qwen3 VL 30B A3B Instruct has no public ModelCap Index position as of 22 September 2026: the snapshot lacks enough matched benchmark evidence, or the identity match is unresolved. Its catalogue facts (price, context, providers) are shown without a rank.

How much does Qwen3 VL 30B A3B Instruct cost per 1M tokens?

Qwen3 VL 30B A3B Instruct is listed at $0.13 per 1M input tokens and $0.52 per 1M output tokens as of 22 September 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 $0.52 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 Qwen3 VL 30B A3B Instruct?

Qwen3 VL 30B A3B Instruct has a published context window of 262K tokens (262,144) 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 Qwen3 VL 30B A3B Instruct open-weight?

Open weights (apache-2.0). 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 Qwen/Qwen3-VL-30B-A3B-Instruct on Hugging Face.

Which API providers serve Qwen3 VL 30B A3B Instruct?

4 providers serve Qwen3 VL 30B A3B Instruct through OpenRouter as of 22 September 2026: Alibaba, DeepInfra, Novita and SiliconFlow. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

Which benchmarks has Qwen3 VL 30B A3B Instruct been evaluated on?

Qwen3 VL 30B A3B Instruct has published results on 2 public boards tracked by ModelCap as of 22 September 2026: AA τ²-Bench Telecom 19.0% (#360 of 436) and AA Humanity's Last Exam 6.3% (#370 of 615). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

When was Qwen3 VL 30B A3B Instruct released?

Qwen3 VL 30B A3B Instruct first appeared in the catalogue on 6 Oct 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.