Alibaba (Qwen) › Qwen 2 72B Instruct › Pricing
Qwen 2 72B Instruct pricing
Cheapest host: DeepInfra · checked Oct 23, 2026
$0.35 / $0.40per 1M tokens in / out
Price sheetper 1M tokens
| Input | $0.35 | DeepInfra |
| Output | $0.40 | |
| Context | 33K | tokens |
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| DeepInfra | $0.35 | $0.40 | — |
In Alibaba (Qwen)'s line-upper 1M in / out
| Qwen2.5 7B Instruct | $0.17 / $0.70 | −16% |
| Qwen3 8B | $0.18 / $0.70 | −14% |
| QVQ 72B Preview | $0.25 / $0.50 | −14% |
| Qwen 2 72B Instruct | $0.35 / $0.40 | this model |
| Qwen 3.6 Flash 2026-04-16 | $0.17 / $0.99 | +2% |
| Qwen3 Next 80B A3B | $0.14 / $1.20 | +12% |
| Qwen 3 Next 80B Instruct | $0.15 / $1.20 | +14% |
Cheaper for the same workvs Qwen 2 72B Instruct
| GLM 5.3 Flash unstatedOpen | -34% | score wins 77% | $0.15 / $0.50 |
| Hy3 unstatedOpen | -36% | score wins 76% | $0.13 / $0.53 |
| Gemma 4 31B unstatedOpen | -56% | score wins 76% | $0.10 / $0.34 |
| GPT-6 Luna max | -45% | score wins 75% | $0.068 |
| Gemma 4 26B A4B unstatedOpen | -28% | score wins 73% | $0.15 / $0.60 |
Pricing questions
How much does Qwen 2 72B Instruct cost?›
$0.35 per 1M input tokens and $0.40 per 1M output tokens.
Is Qwen 2 72B Instruct free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
What is a cheaper alternative to Qwen 2 72B Instruct?›
GLM 5.3 Flash at unstated effort costs -34% per task with a score wins 77% on Arena Text · overall.