LLM Reference

Qwen3-VL-235B-A22B

Released
2025-12-01
Last refreshed
2026-06-29
Status
Researched 31d ago
Open sourceCommercial use: permittedMultimodalRAGLong contextVisionJSON / Tool use

Qwen3-VL-235B-A22B is worth evaluating for rag, long context, and vision when its provider route and context window match the workload.

Use it for

  • Teams evaluating rag, long context, and vision
  • Workloads that can use a 128k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Qwen3-VL
Released
2025-12-01
Context
128k
Parameters
235B (22B active)
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Unknown
Code
Unknown
Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
$2.60
Input / 1M
$0.260

Cheapest of 3 routes · OpenRouter

About

Qwen3-VL-235B-A22B is Alibaba's Qwen3-VL model. It was released 2025-12-01.

Qwen3-VL-235B-A22B is an open-source model in the Qwen3-VL family. The structured metadata tracks a 128k-token context window, multimodal input, and structured outputs. This page tracks provider routes through AWS Bedrock, OpenRouter, and Novita AI, with the cheapest tracked route listed at $0.26 input and $2.6 output per 1M tokens. Headline tracked benchmarks include MMMU Pro 69.3.

Top use-case fit

RAG

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
OpenRouter$0.260$2.60
Serverless
AWS Bedrock$0.530$2.66
Serverless
Novita AI$0.980$3.95
Serverless

Available via routers & gateways(1)

Capabilities

VisionMultimodalStructured Outputs

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
MMMU Pro69.3LLM-Stats aggregator, thinking mode (highest)https://llm-stats.com/benchmarks/mmmu-pro

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Qwen3-VL-235B-A22B?

Qwen3-VL-235B-A22B has a context window of 128k tokens.

How much does Qwen3-VL-235B-A22B cost?

Qwen3-VL-235B-A22B pricing ranges from $0.26/1M to $0.98/1M input tokens depending on the provider.

When was Qwen3-VL-235B-A22B released?

Qwen3-VL-235B-A22B was released on 2025-12-01.

Which providers offer Qwen3-VL-235B-A22B?

Qwen3-VL-235B-A22B is available from 3 providers: AWS Bedrock, OpenRouter, Novita AI.

What benchmarks has Qwen3-VL-235B-A22B been tested on?

Qwen3-VL-235B-A22B has been evaluated on 1 benchmark, including MMMU Pro.