Qwen
Qwen3 VL 235B A22B Instruct
Released 2025-09-23 · Knowledge up to 2025-03-31
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...
You send / 1M
$0.210
tokens in
It replies / 1M
$1.90
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0012
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp8 | $0.200 | $0.880 | 99% | Read |
| Venice · fp8 | $0.210 | $1.90 | 96% | Read |
| Parasail · fp8 | $0.210 | $1.90 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image
- Writes: text
- Reasoning: No
- Tool calling: Yes
- Longest reply: 33K tokens
- Repeated text is billed at $0.100 per 1M (prompt caching)
- Intelligence score: 9.9 / 100 (Artificial Analysis)
Similar models
- Mistral Medium 3.1Mistral · $0.400 in / $2.00 out per 1M
- Mistral Medium 3Mistral · $0.400 in / $2.00 out per 1M
- GPT-4.1 MiniOpenAI · $0.400 in / $1.60 out per 1M
- Mistral Large 3 2512Mistral · $0.500 in / $1.50 out per 1M
- Nano Banana (Gemini 2.5 Flash Image)Google · $0.300 in / $2.50 out per 1M
- Pareto 26.10Unbiased · $0.800 in / $3.20 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Vision AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Vision AI ModelsTop No-Training Vision Tool-Calling AI ModelsTop No-Training Tool-Calling AI ModelsTop Zero Data Retention AI Models
Estimate your monthly cost with Qwen3 VL 235B A22B Instruct →