Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

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

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

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

Qwen: Qwen3 VL 235B A22B Thinking

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

Model weights
Compare

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. 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

$0.40 / $4per 1M

Context

131K

Released

Sep 23, 2025

Knowledge Cutoff

Mar 2025

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQ

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 Exacto (highest tool-calling accuracy).

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. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

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.

Quick Start

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.

About Qwen: Qwen3 VL 235B A22B Thinking

OpenRouter makes Qwen: Qwen3 VL 235B A22B Thinking available through a unified, OpenAI-compatible API using the model ID qwen/qwen3-vl-235b-a22b-thinking. Requests can be routed across 2 providers, including Alibaba Cloud Int. and NovitaAI, with automatic failover when an endpoint is unavailable.

Qwen: Qwen3 VL 235B A22B Thinking accepts text and images and returns text. It has a 131,072-token context window and a maximum output of 32,768 tokens.

On OpenRouter, Qwen: Qwen3 VL 235B A22B Thinking costs $0.40/M input tokens and $4.00/M output tokens. It was released on September 23, 2025; its knowledge cutoff is March 31, 2025.

More models from Qwen

  • Qwen3.8 27B
  • Qwen3 Reranker 8B
  • Qwen3 ASR 1.7B

Frequently asked questions

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math.

Qwen3 VL 235B A22B Thinking costs $0.40/M input tokens and $4.00/M output tokens.

Qwen3 VL 235B A22B Thinking has a 131,072 token context window. It supports up to 32,768 completion tokens.

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

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

Qwen3 VL 235B A22B Thinking is served by 2 providers on OpenRouter: Alibaba Cloud Int. and NovitaAI. 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 Thinking was released on September 23, 2025. Its knowledge cutoff is March 31, 2025.

$0.98$3.950.95s38 tps
99.86%
$0.40$4.000.61s56 tps
86.01%

Throughput

56tok/s

P50, best across providers

Latency

0.61s

P50, best provider

Uptime (3d)

100.00%

Availability (3d)

99.17%

Availability over the last 3 days

Last 72 hours
Availability 99.17%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.65%
Without Routing
90.68%

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 customization options.

1.
Favicon for https://github.com/litroz/vehiclefrauddetectionapi
Litroz Vehicle Fraud Detection
new
99.5Mtokens
2.
Favicon for https://github.com/ReefNet/eccv2026
ReefNet zero-shot coral genus classification
new
43.6Mtokens
3.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
41Mtokens
4.
Favicon for https://janitorai.com/
Janitor AI
Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.
30.2Mtokens
5.
Favicon for https://portkey.ai/
Portkey AI
Control panel for AI apps
19.9Mtokens