Qwen2.5 72B Instruct — pricing & benchmarks

By qwen · Updated 2026-10-06 · Open weights · custom licensecheap high-volumeopen weights / self-hostable

What Qwen2.5 72B Instruct is used for

Qwen2.5 72B Instruct is best suited for cheap high-volume, open weights / self-hostable. Access it through one Appmo API key alongside 458 other models — Appmo's optimizer can route to it automatically when it is the best value for a request. Weights: huggingface.co/Qwen/Qwen2.5-72B-Instruct.

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"qwen/qwen-2.5-72b-instruct","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does Qwen2.5 72B Instruct cost?
Qwen2.5 72B Instruct costs $0.36 per 1M input tokens and $0.4 per 1M output tokens ($0.37 blended), as of 2026-10-06. Prices are expected to fall as competition increases.

What is Qwen2.5 72B Instruct best for?
Qwen2.5 72B Instruct is best suited for cheap high-volume, open weights / self-hostable.

How do I use Qwen2.5 72B Instruct?
Send requests to Appmo's OpenAI-compatible endpoint with model id "qwen/qwen-2.5-72b-instruct" and one API key — no separate provider account needed.

Is Qwen2.5 72B Instruct open source?
Yes — its weights are public on Hugging Face (Qwen/Qwen2.5-72B-Instruct) under a custom license; check the license terms before commercial use.

Can Qwen2.5 72B Instruct create images?
No, Qwen2.5 72B Instruct works with text.