Qwen-72BvsQwen3
Qwen-72B | Qwen3 | |
|---|---|---|
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | 72B | 235B |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 32k | 128k |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.70 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $2.80 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.0482StreamLake |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $0.1931StreamLake |
| Overview | ||
| Company | Qwen | Qwen |
| Release date | Nov 30 2023 | Apr 29 2025 |
| Access | Open Weight | Open Weight |
Other comparisons
Frequently asked questions
Qwen-72B and Qwen3 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Qwen3 has a verified first-party API price: $0.70 per million input tokens and $2.80 per million output tokens. No pay-as-you-go API rate is tracked for Qwen-72B. Qwen-72B shipped 516 days before Qwen3, so benchmark comparisons should account for the intervening progress.
Qwen-72B has 72B parameters, while Qwen3 has 235B. Context windows are 32k (Qwen-72B) vs 128k (Qwen3).
Direct benchmark comparisons are unavailable — Qwen-72B and Qwen3 don't publish scores on any of the same benchmarks.