Qwen3 VL 235B A22B Thinking
Qwen3 VL 235B A22B Thinking is Alibaba's language model with a 262K context window and up to 33K output tokens, available from 5 providers, starting at $0.220 / 1M input and $0.880 / 1M output. A thinking-mode vision-language MoE model with 235B total and 22B activated parameters, combining enhanced visual perception with extended chain-of-thought reasoning.
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 Fireworks AI | $0.220 | $0.880 | — | — |
 OpenRouter | $0.260 | $2.60 | — | — |
Alibaba Qwen | $0.400 | $4.00 | $0.200 | $2.00 |
 Hugging Face | $0.980 | $3.95 | — | — |
 Novita | $0.980 | $3.95 | — | — |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen3 VL 30B A3B Instruct | 262K | $0.130 | $0.520 | Available | |
| Qwen3 VL 30B A3B Thinking | 262K | $0.130 | $0.600 | Available | |
| Qwen3 VL 235B A22B Thinking | 262K | $0.220 | $0.880 | Current | |
| Qwen3 VL 235B A22B Instruct | 262K | $0.200 | $0.880 | Available |