Qwen3 VL 30B A3B Instruct

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 of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.

alibaba/qwen3-vl-30b-a3b-instruct

Organization: Alibaba
Family: qwen
Providers: 8
Context: 262,144
Output limit: 32,768
Knowledge: —
Release: 2025-10-04
Updated: 2025-10-04
Weights: Open
Input: text, image, video
Output: text
Capabilities: Tools, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

10 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Deep Infra	Qwen/Qwen3-VL-30B-A3B-Instruct	262,144	32,768	$0.15 / $0.60	No	Yes	Yes	View
Eden AI	deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct	262,144	32,768	$0.15 / $0.60	No	Yes	Yes	View
Hugging Face	Qwen/Qwen3-VL-30B-A3B-Instruct	131,072	32,768	$0.20 / $0.70	No	Yes	Yes	View
Kilo Gateway	qwen/qwen3-vl-30b-a3b-instruct	262,144	16,384	$0.15 / $0.60	No	Yes	Yes	View
Merge Gateway	qwen/qwen3-vl-30b-a3b-instruct	131,072	32,768	$0.108 / $0.43	No	Yes	Yes	View
Novita AI	qwen/qwen3-vl-30b-a3b-instruct	131,072	32,768	$0.20 / $0.70	No	Yes	Yes	View
DeepInfravia OpenRouter	qwen/qwen3-vl-30b-a3b-instruct fp8	262,144	16,384	$0.15 / $0.60	No	Yes	Yes	View
Novitavia OpenRouter	qwen/qwen3-vl-30b-a3b-instruct bf16	131,072	32,768	$0.20 / $0.70	No	Yes	Yes	View
SiliconFlowvia OpenRouter	qwen/qwen3-vl-30b-a3b-instruct fp8	262,144	235,929	$0.29 / $1.00	No	Yes	Yes	View
Prime Inference	qwen/qwen3-vl-30b-a3b-instruct	262,144	16,384	$0.20 / $0.70	No	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.108Per 1M input tokens

Output from$0.43Per 1M output tokens

Available offers10Across 8 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 3 lowest-priced configurations

InputOutput

DeepInfradeepinfra/fp8

$0.15$0.60

Novitanovita/bf16

$0.20$0.70

SiliconFlowsiliconflow/fp8

$0.29$1.00

qwen/qwen3-vl-30b-a3b-instructObserved Oct 10, 2026, 11:31 AM UTC

Input: $0.15
Output: $0.60

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
DeepInfradeepinfra/fp8	$0.15	$0.60	—	—
Novitanovita/bf16	$0.20	$0.70	—	—
SiliconFlowsiliconflow/fp8	$0.29	$1.00	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 3 endpoints

P50P75P90P99

DeepInfradeepinfra/fp8

493–4,418.62 ms

Novitanovita/bf16

3,029–8,634.72 ms

SiliconFlowsiliconflow/fp8

1,887–6,208.47 ms

All latency percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
DeepInfradeepinfra/fp8	493 ms	1,197 ms	1,939.9 ms	4,418.62 ms
Novitanovita/bf16	3,029 ms	4,746 ms	6,422 ms	8,634.72 ms
SiliconFlowsiliconflow/fp8	1,887 ms	2,592 ms	3,758.6 ms	6,208.47 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 3 endpoints

P50P75P90P99

DeepInfradeepinfra/fp8

30–45 t/s

Novitanovita/bf16

25–49 t/s

SiliconFlowsiliconflow/fp8

17–39.78 t/s

All throughput percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
DeepInfradeepinfra/fp8	30 t/s	35 t/s	39 t/s	45 t/s
Novitanovita/bf16	25 t/s	36 t/s	42 t/s	49 t/s
SiliconFlowsiliconflow/fp8	17 t/s	20 t/s	22 t/s	39.78 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 3 endpoints

Endpoint5 minutes30 minutes24 hours

DeepInfradeepinfra/fp8Observed Oct 10, 2026, 11:31 AM UTC

100%

99.93%

Novitanovita/bf16Observed Oct 10, 2026, 11:31 AM UTC

100%

96.55%

92.87%

SiliconFlowsiliconflow/fp8Observed Oct 10, 2026, 11:31 AM UTC

100%

82.68%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

qwen/qwen3-vl-30b-a3b-instructObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 10

Intelligence

7.9

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

gpqa diamondQwen: Qwen3 VL 30B A3B Instruct

64.579%

tau bench verified airlineQwen: Qwen3 VL 30B A3B Instruct

35.676%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct	OpenRouter	64.579%	Details
tau bench verified airline	Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct	OpenRouter	35.676%	Details
Composite indices	Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct	Artificial Analysis	Intelligence 7.9 · Coding — · Agentic —	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 15, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

qwen/qwen3-vl-30b-a3b-instructObserved Oct 10, 2026, 11:31 AM UTC

Context: 262,144
Maximum output: 16,384
Tokenizer: Qwen3
Input: text, image
Output: text
Moderation: No
Knowledge cutoff: 2025-03-31
Added to OpenRouter: 2025-10-06

Base URLhttps://openrouter.ai/api/v1

Model IDqwen/qwen3-vl-30b-a3b-instruct

Version IDqwen/qwen3-vl-30b-a3b-instruct

Weights IDQwen/Qwen3-VL-30B-A3B-Instruct

Supported parameters

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

Default parameters

top k: 20
top p: 0.8
temperature: 0.7
repetition penalty: 1

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Qwen3 VL 30B A3B Instruct cost?

Listed rates start at $0.108 per million input tokens and $0.43 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Qwen3 VL 30B A3B Instruct?

There are 10 cataloged offers across 8 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 262,144 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

Apache-2.0

Hugging Face ↗

Catalog history · 1 recorded revision

Metadata observations since this model was first cataloged. These are not model release versions.

Oct 10, 2026 · 6cd1cc0687c5