Alibaba logo

Qwen3 VL 235B A22B Instruct

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Qwen3 VL 235B A22B Instruct is Alibaba's language model with a 262K context window and up to 129K output tokens, available from 9 providers, starting at $0.2 / 1M input and $0.88 / 1M output. The flagship instruction-tuned vision-language MoE model in the Qwen3 series, with 235B total and 22B activated parameters for superior visual perception and reasoning.
Specifications
Canonical IDalibaba-qwen3-vl-235b-a22b-instruct
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window262K tokens
Max Output129K tokens
Input ModalitiesImagePDFText
Output ModalitiesText
Parameters235B
HuggingFace Likes383
HuggingFace Downloads (30d)947,793
HuggingFace Downloads (all-time)2,172,030
Release Date · 1 year ago
Knowledge Cutoff · 2 years ago
Benchmarks
Intelligence Index
#316
Math Index
#124
MMLU-Pro
#79
GPQA
#261
HLE
#313
LiveCodeBench
#142
IFBench
#240
Time to First Token
#457
SciCode
#259
AIME 2025
#124
LCR
#311
TerminalBench Hard
#244
TAU2
#231
Output TPS
#236

Capabilities

Input3/5
Text✓
Image✓
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
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
ProviderStandardFlex
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Input
$ / 1M
Output
$ / 1M
Alibaba Qwen logo
Alibaba Qwen
dashscope/qwen3-vl-235b-a22b-instruct
$0.4$1.60N/A——
Amazon Bedrock logo
Amazon Bedrock
bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct
$0.53$2.66N/A$0.26$1.33
DeepInfra logo
DeepInfra
deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct
$0.2$0.88$0.11——
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct
$0.22$0.88N/A——
GMI Cloud logo
GMI Cloud
gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8
$0.3$1.40N/A——
Novita logo
Novita
novita/qwen/qwen3-vl-235b-a22b-instruct
$0.3$1.50N/A——
OpenRouter logo
OpenRouter
qwen/qwen3-vl-235b-a22b-instruct
$0.21$1.90$0.1——
Qwen AI Platform
qwen_ai_platform/qwen3-vl-235b-a22b-instruct
$0.4$1.60N/A——
Qwencloud
qwencloud/qwen3-vl-235b-a22b-instruct
$0.4$1.60N/A——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen3 VL 235B A22B Instruct, ranked by cheapest on-demand price. The model needs about 564 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
p4de.24xlargeAWS8× A100640 GB$27.45/hr
Standard_ND96amsr_A100_v4Azure8× NVIDIA A100 (80GB)640 GB$32.77/hr
g7e.48xlargeAWS8× RTX PRO Server 6000768 GB$33.14/hr
7 more instances can run Qwen3 VL 235B A22B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Qwen3 VL 30B A3B Instruct262K$0.150$0.600Available
Qwen3 VL 30B A3B Thinking262K$0.150$0.600Deprecated
Qwen3 VL 235B A22B Instruct262K$0.200$0.880Current
Qwen3 VL 235B A22B Thinking262K$0.220$0.880Deprecated

Model IDs

accounts/fireworks/models/qwen3-vl-235b-a22b-instruct
alibaba-qwen3-vl-235b-a22b-instruct
alibaba/qwen3-vl-235b-a22b-instruct
bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct
dashscope/qwen3-vl-235b-a22b-instruct
deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct
fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct
gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8
novita/qwen/qwen3-vl-235b-a22b-instruct
openrouter/qwen/qwen3-vl-235b-a22b-instruct
qwen_ai_platform/qwen3-vl-235b-a22b-instruct
qwen/qwen3-vl-235b-a22b-instruct
Qwen/Qwen3-VL-235B-A22B-Instruct
qwen3-vl-235b-a22b-instruct
qwencloud/qwen3-vl-235b-a22b-instruct