Model: Qwen: Qwen3 VL 235B A22B Thinking, Context: 131072, Cost: $0.7 per 1M input tokens, $8.4 per 1M output tokens
Note: Calculation is approximate based on public data. Prices may change, check official websites.
This calculator estimates the cost of using the Qwen3 VL 235B A22B Thinking model, an advanced multimodal AI capable of strong text generation and visual understanding across images and video. Optimized for multimodal reasoning, especially in STEM and math, it excels in perception, spatial understanding, and long-form visual comprehension.
The model's pricing is based on token usage:
- Input tokens: $0.7 per 1 million tokens
- Output tokens: $8.4 per 1 million tokens
- Context window: 131,072 tokens
The total cost is calculated using the following formula:
Total Cost = (Input Tokens / 1,000,000) * $0.7 + (Output Tokens / 1,000,000) * $8.4
Example: If you process 50,000 input tokens and generate 10,000 output tokens for a single request, the cost would be:
(50,000 / 1,000,000) * $0.7 + (10,000 / 1,000,000) * $8.4 = $0.035 + $0.084 = $0.119