gpudiff the public record of change in GPU cloud pricing
Follow the diffs: RSS · Free API · Sponsor this site

qwen2.5-72b-instruct API price — 2 gateways compared

from $0.23 per million input tokens · 1.6× spread between gateways · updated hourly

Gateway$ in /MTok$ out /MTok ContextInput price historyModel ID
Requesty$0.23$0.40131,072since 2026-08-20deepinfra/Qwen/Qwen2.5-72B-Instruct
DeepInfra$0.36$0.4032,768since 2026-08-20Qwen/Qwen2.5-72B-Instruct

Changelog for qwen2.5-72b-instruct

qwen2.5-72b-instruct pricing FAQ

How much does qwen2.5-72b-instruct cost per million tokens?

The cheapest tracked gateway charges $0.23 per million input tokens and $0.40 per million output tokens (Requesty). Prices refresh hourly.

Which gateway is cheapest for qwen2.5-72b-instruct?

Requesty for input tokens and DeepInfra for output tokens, among the 2 gateways we track.

Do qwen2.5-72b-instruct prices differ between gateways?

Yes — the most expensive tracked gateway charges 1.6× the cheapest for input tokens. Identical model, identical tokens, different bill.

← All LLM prices · API