Alibaba
Qwen3 VL 235B A22B Instruct
Qwen vision-language instruct model for visual reasoning, documents, and agent tasks
Model facts
- Context window
- 262K tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.2 per 1M tokens
- Cheapest paid output
- $0.88 per 1M tokens
- Open weights
- yes
- Providers
- 2
Capabilities and modalities
tool calling, attachments, temperature control, open weights, text, image.
Local hardware estimate
At 4K context: Q4_K_M 127.3 GiB, Q8_0 237.0 GiB, F16 442.8 GiB working memory.
- Parameters
- 235.7 billion
- Architecture
- qwen3vlmoe
- Model license
- apache-2.0
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 14.4 | not measured | 70.7 | not measured |
Observed price history
- 2026-08-24: $0.2 input / $0.88 output per 1M tokens
API providers
- LLM Gateway (DeepInfra) — model id deepinfra/qwen3-vl-235b-a22b-instruct; $0.2 input / $0.88 output per 1M tokens; provider documentation
- LLM Gateway (NovitaAI) — model id novita/qwen3-vl-235b-a22b-instruct; $0.3 input / $1.5 output per 1M tokens; provider documentation