Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for qwen

Qwen: Qwen3 VL 235B A22B Instruct

qwen/qwen3-vl-235b-a22b-instruct

Model weights
Compare

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.

Beyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows—turning sketches or mockups into code and assisting with UI debugging—while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.

Modalities
In / Out Price
$0.20 / $0.88per 1M
Context
262K
Released
Sep 23, 2025
Knowledge Cutoff
Mar 2025
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Qwen: Qwen3 VL 235B A22B Instruct (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisQwen3 235B A22B (Non-reasoning) Intelligence Index8.3
Artificial AnalysisQwen3 235B A22B (Non-reasoning) Math Index23.7
Artificial AnalysisQwen3 235B A22B (Non-reasoning) GPQA Diamond61.3%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) HLE4.2%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) IFBench36.6%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) τ²-Bench Telecom27.2%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) AA-LCR0.0%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) CritPt0.0%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) LiveCodeBench34.3%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) Terminal-Bench Hard6.1%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) MMLU-Pro76.2%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) AA-Omniscience Accuracy18.6%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) AA-Omniscience Non-Hallucination Rate12.9%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) AIME 202523.7%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) AIME32.7%
Artificial AnalysisQwen3 235B A22B (Non-reasoning) MATH-50090.2%
Artificial AnalysisQwen3 VL 235B A22B Instruct Intelligence Index9.9
Artificial AnalysisQwen3 VL 235B A22B Instruct Math Index70.7
Artificial AnalysisQwen3 VL 235B A22B Instruct GPQA Diamond71.2%
Artificial AnalysisQwen3 VL 235B A22B Instruct HLE6.6%
Artificial AnalysisQwen3 VL 235B A22B Instruct IFBench42.7%
Artificial AnalysisQwen3 VL 235B A22B Instruct τ²-Bench Telecom35.1%
Artificial AnalysisQwen3 VL 235B A22B Instruct AA-LCR32.7%
Artificial AnalysisQwen3 VL 235B A22B Instruct CritPt0.0%
Artificial AnalysisQwen3 VL 235B A22B Instruct LiveCodeBench59.4%
Artificial AnalysisQwen3 VL 235B A22B Instruct Terminal-Bench Hard6.8%
Artificial AnalysisQwen3 VL 235B A22B Instruct MMLU-Pro82.3%
Artificial AnalysisQwen3 VL 235B A22B Instruct AA-Omniscience Accuracy20.3%
Artificial AnalysisQwen3 VL 235B A22B Instruct AA-Omniscience Non-Hallucination Rate8.4%
Artificial AnalysisQwen3 VL 235B A22B Instruct AIME 202570.7%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
Latency / throughput
$0.21$1.90$0.101.18s32 tps
97.55%
$0.21$1.90$0.101.08s15 tps
100.00%
$0.20$0.88$0.112.40s6 tps
97.84%
Throughput
32tok/s

P50, best across providers

Latency
1.08s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchPrimeIntellect70.7%48.0%Novita71.4%45.3%Alibaba71.5%42.7%Parasail71.4%41.3%Venice69.9%42.7%
+2 more providers
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.96%

Availability over the last 3 days

Last 72 hours
Availability 99.96%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.97%
Without Routing
91.74%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Frequently asked questions

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR).

Qwen3 VL 235B A22B Instruct costs $0.20/M input tokens and $0.88/M output tokens, with separate rates for Cache Read at $0.11/M tokens.

Qwen3 VL 235B A22B Instruct has a 262,144 token context window. It supports up to 16,384 completion tokens.

Yes. Qwen3 VL 235B A22B Instruct accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Qwen3 VL 235B A22B Instruct accepts text and images as input and returns text.

Qwen3 VL 235B A22B Instruct is served by 3 providers on OpenRouter: DeepInfra, Venice, and Parasail. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Qwen3 VL 235B A22B Instruct was released on September 23, 2025. Its knowledge cutoff is March 31, 2025.