Alibaba logo

Qwen3 VL 30B A3B Instruct

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Qwen3 VL 30B A3B Instruct is Alibaba's language model with a 262K context window and up to 33K output tokens, available from 5 providers, starting at $0.13 / 1M input and $0.52 / 1M output. An instruction-tuned vision-language MoE model with 30B total and 3B activated parameters, offering strong multimodal understanding and generation capabilities.
Specifications
Canonical IDalibaba-qwen3-vl-30b-a3b-instruct
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window262K tokens
Max Output33K tokens
Input ModalitiesImageText
Output ModalitiesText
Parameters30B
HuggingFace Likes562
HuggingFace Downloads (30d)2,219,395
HuggingFace Downloads (all-time)14,070,852
Release Date · 10 months ago
Knowledge Cutoff · 1 year ago
Benchmarks
Intelligence Index
10.0
#296
Math Index
72.3
#85
MMLU-Pro
0.8
#146
GPQA
0.7
#213
HLE
0.1
#231
LiveCodeBench
0.5
#143
IFBench
0.3
#308
Time to First Token
0.94s
#354
SciCode
0.3
#237
AIME 2025
0.7
#85
LCR
0.2
#253
TerminalBench Hard
0.1
#246
TAU2
0.2
#322
Output TPS
126.4
#94

Capabilities

Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Alibaba Qwen logo
Alibaba Qwen
qwen3-vl-30b-a3b-instruct
$0.2$0.8$0.1$0.4
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct
$0.15$0.6——
Hugging Face logo
Hugging Face
novita:qwen/qwen3-vl-30b-a3b-instruct
$0.2$0.7——
Novita logo
Novita
novita/qwen/qwen3-vl-30b-a3b-instruct
$0.2$0.7——
OpenRouter logo
OpenRouter
qwen/qwen3-vl-30b-a3b-instruct
$0.13$0.52——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen3 VL 30B A3B Instruct, ranked by cheapest on-demand price. The model needs about 72 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP20sAzure2× AMD Alveo U250 FPGA (64GB)128 GB$3.30/hrwestus2
g7e.2xlargeAWSRTX PRO Server 600096 GB$3.36/hrus-east-1
Standard_NC24ads_A100_v4AzureNVIDIA A10080 GB$3.67/hrwestus2
7 more instances can run Qwen3 VL 30B A3B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Qwen3 VL 30B A3B Instruct262K$0.130$0.520Current
Qwen3 VL 30B A3B Thinking262K$0.130$0.600Available
Qwen3 VL 235B A22B Instruct262K$0.210$0.880Available
Qwen3 VL 235B A22B Thinking262K$0.220$0.880Available

Model IDs

accounts/fireworks/models/qwen3-vl-30b-a3b-instruct
alibaba-qwen3-vl-30b-a3b-instruct
fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct
novita/qwen/qwen3-vl-30b-a3b-instruct
qwen/qwen3-vl-30b-a3b-instruct
Qwen/Qwen3-VL-30B-A3B-Instruct
qwen3-vl-30b-a3b-instruct