← model directory

qwen

Qwen: Qwen3 VL 235B A22B Thinking

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

↓ runs free on your own hardware⚙ tool calling

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....

specs & pricing
Type
text
Provider
qwen
Model ID
qwen/qwen3-vl-235b-a22b-thinking
Capabilities
vision, tools, reasoning
Context window
131K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.44 / 1M tokens
Output price
$4.40 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$4.84

$0.44 for a million input tokens plus $4.40 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

Run it on your own hardware

Estimated GPU memory for Qwen: Qwen3 VL 235B A22B Thinking (235B parameters), for the weights alone — add room for the context cache.

Q4_K_M
~134.3 GBmulti-GPU or large unified memory
Q8_0
~232.7 GBmulti-GPU or large unified memory
FP16 / BF16
~438.5 GBmulti-GPU or large unified memory

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

/// initialize

Call Qwen: Qwen3 VL 235B A22B Thinking through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of Qwen: Qwen3 VL 235B A22B Thinking?
Qwen: Qwen3 VL 235B A22B Thinking accepts up to 131,072 tokens (131K) of context per request.
How much does Qwen: Qwen3 VL 235B A22B Thinking cost per million tokens?
Through Wide Area Intelligence, Qwen: Qwen3 VL 235B A22B Thinking costs $0.44 per 1M input tokens and $4.40 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $4.84.
Can I run Qwen: Qwen3 VL 235B A22B Thinking on my own hardware?
Yes — Qwen: Qwen3 VL 235B A22B Thinking is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 134.3 GB of GPU memory, plus room for the context cache — more than a single 80 GB card, so plan for multiple GPUs or a large unified-memory machine. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from qwen

← browse all models