Qwen3-VL-235B-A22B Instruct

  • Open weights
  • Standard
  • Input: text · image
  • Released 2025-09
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 50.7
CoverageIndex weight that has results.10%
SpeedOutput tokens per second.32/sMedian 76/s
First tokenSeconds to the first output token.1.0 sMedian 1.1 s
Input / 1MUS dollars per 1M input tokens.$0.21Median $0.60
Output / 1MUS dollars per 1M output tokens.$1.90Median $2.50
ContextMaximum tokens in one request.262KMedian 262K
EloLMArena rating and rank.1420±7 #120Median 1425

Details

From OpenRouter
API IDThe model ID on OpenRouter.
qwen/qwen3-vl-235b-a22b-instruct
Max outputMaximum output tokens per request.
33K
Knowledge cutoffLast date of training data.
31 Mar 2025
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.10
Weights
Hugging Face (opens in a new tab) ↗
RetiresDate OpenRouter removes the model.
—

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.4 counted45.7—
KnowledgeFacts and expert knowledge.None counted——
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.None counted——

Results

4 counted
BenchmarkResultThe score from the source.PlacePlace among results on this benchmark.
RealWorldQAMultimodal79.3%13 / 19
ScreenSpot ProMultimodal62.0%17 / 22
CC-OCRMultimodal82.2%—
Video-MME without subtitleMultimodal79.2%—
VideoMMMUMultimodal74.7%—
OCRBench V2Multimodal67.1%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reusemodels.devMITCheaper InferenceNo licence stated

History

13 releases
Output / 1M$1.90 → $1.90
18 Nov 202621 Nov 2026

Questions

How much does Qwen3-VL-235B-A22B Instruct cost?
$0.21 per 1M input tokens, $1.90 per 1M output tokens.
How fast is Qwen3-VL-235B-A22B Instruct?
32 output tokens per second, 1.0 s to the first token.
What is the context window of Qwen3-VL-235B-A22B Instruct?
262K tokens.
Is Qwen3-VL-235B-A22B Instruct open source?
Yes. Its weights are published.
When was Qwen3-VL-235B-A22B Instruct released?
September 2025.

More from Alibaba

All models
Qwen3 Coder PlusUnrankedQwen3 VL 235B A22B ThinkingUnrankedQwen3 Max44.8Qwen3-Omni-30B-A3B-InstructUnrankedQwen3-Omni-30B-A3B-ThinkingUnranked