Model pricing

Qwen2.5 72B Instruct API Pricing

Compare 3 providers offering Qwen2.5 72B Instruct. Cheapest quote is $0.360 per 1M input tokens.

Providers: 3
Official: —
Cheapest: $0.360
Context: 33K

Provider pricing

Estimate my cost

Input tokens / dayOutput tokens / day

Period

based on 30 days

Provider	Input	Output	Cached input	Context	vs official	Your cost
OpenRouterAggregator 17.3M	$0.360	$0.400	—	33K	—	$13cheapest	Use
DeepInfraInference platform	$0.360	$0.400	—	33K	—	$13cheapest
NovitaInference platform	$0.380	$0.400	—	32K	—	$14+$0.600

Prices captured Jul 26, 2026

Prices change frequently and promotional rates expire — always confirm on the provider's own pricing page before committing. Rates far below official pricing often indicate shared or resold accounts.