Qwen/Qwen2.5-72B-Instruct
As of Nov 22, 2026, the cheapest Qwen/Qwen2.5-72B-Instruct API price is $0.59 per 1M input tokens (SiliconFlow) and $0.59 per 1M output tokens (SiliconFlow). Qwen/Qwen2.5-72B-Instruct is offered by 2 providers in the qwen family, open weights.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.
| SiliconFlowopenQwen/Qwen2.5-72B-Instruct | Cheapest$0.59 | Cheapest$0.59 | — | — | 33k | — |
| SiliconFlow (China)openQwen/Qwen2.5-72B-Instruct | $0.6172 | $0.6172 | — | — | 33k | 31d ago |
Qwen/Qwen2.5-72B-Instruct price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the one provider whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| SiliconFlow (China) | $0.59 → $0.6172 | $0.59 → $0.6172 | +4.6% |
Qwen/Qwen2.5-72B-Instruct pricing FAQ
What is the cheapest Qwen/Qwen2.5-72B-Instruct API?
As of Nov 22, 2026, SiliconFlow has the lowest Qwen/Qwen2.5-72B-Instruct output price at $0.59 per 1M tokens, and SiliconFlow has the lowest input price at $0.59 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Qwen/Qwen2.5-72B-Instruct?
2 providers list Qwen/Qwen2.5-72B-Instruct on Sovyron; 2 of them sell it at a metered per-token price.
Is Qwen/Qwen2.5-72B-Instruct free?
No provider in the Sovyron catalog lists a free tier for Qwen/Qwen2.5-72B-Instruct.
What is the context window of Qwen/Qwen2.5-72B-Instruct?
Qwen/Qwen2.5-72B-Instruct supports a 33k-token context window and up to 4k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—