LLM token calculator
Qwen3 VL 30B A3B Thinking Cost Calculator
Work out what Qwen3 VL 30B A3B Thinking will cost per month. It is priced at $0.2 per 1M input tokens and $2.4 per 1M output tokens. Move the sliders to match your traffic.
Requests / month100,000
Input tokens / request1,500
Output tokens / request400
150.0M input + 40.0M output tokens / month
Estimated Qwen3 VL 30B A3B Thinking bill
$126/mo
$1.26 per 1,000 requests
Full Qwen3 VL 30B A3B Thinking pricing →Same workload on other models
- Mistral NemoMistral AI$4.05/mo
- gpt-oss-20bOpenAI$6.30/mo
- DeepSeek V4 Flash 0423DeepSeek$6.74/mo
- Nex-N2.5-MiniNex AGI$7.75/mo
- Qwen3.7 FlashQwen$9.70/mo
- Schematron V2 TurboInferenceNet$11/mo