Google: Gemini 2.0 Flash vs Qwen2.5 72B Instruct — API Pricing Comparison
Google: Gemini 2.0 Flash is 2% cheaper than Qwen2.5 72B Instruct at the same token volume. Data as of 2026-02-27.
Google: Gemini 2.0 Flash
Total /1M tokens
$0.500Input $0.100 · Output $0.400
Context: 1048K tokens
Full details →Context: 1048K tokens
Qwen2.5 72B Instruct
qwen
Total /1M tokens
$0.510Input $0.120 · Output $0.390
Context: 32K tokens
Full details →Context: 32K tokens
Monthly Cost Comparison
| Monthly usage | Google: Gemini 2.0 Flash | Qwen2.5 72B Instruct | Savings with Google: Gemini 2.0 Flash |
|---|---|---|---|
| 1M tokens/month | $0.50 | $0.51 | $0.01 |
| 10M tokens/month | $5.00 | $5.10 | $0.10 |
| 100M tokens/month | $50.00 | $51.00 | $1.00 |
| 1B tokens/month | $500.00 | $510.00 | $10.00 |
Use both automatically — let AI decide
StormRouter routes each prompt to the cheapest model that meets your quality requirements.
Use Google: Gemini 2.0 Flash for simple tasks, Qwen2.5 72B Instruct only when complexity demands it.