Alibaba / API · Fast · Updated 2026-11

Qwen 2.5 72B API Pricing & Cost Breakdown

Bilingual CJK/English summarization, structured data extraction, and open-weights deployment.

Input / 1M Tokens
$0.35
Cached Input / 1M
$0.350
Output / 1M Tokens
$0.40
Context Window
128K

Workload Cost Scenarios (30-Day Billing)

Reference hosted serverless API rate; can also be self-hosted on cloud GPUs.

Scenario In / Out per Req Uncached Monthly 50% Cache Hit Monthly
Hobby / Prototype (100 req/day) 1500 / 400 $2.05 $2.05
Growing Startup (2,500 req/day) 2500 / 700 $86.63 $86.63
Production Scale (50,000 req/day) 3000 / 800 $2,055.00 $2,055.00

Frequently Asked Questions

What is Qwen 2.5 72B API pricing per 1M tokens?

Standard input is $0.35/1M, cached input is $0.350/1M, and output is $0.40/1M.

What is the context window of Qwen 2.5 72B?

Qwen 2.5 72B supports a 128K token context window with up to 8,192 max output tokens.

How much does prompt caching save on Qwen 2.5 72B?

Prompt caching reduces cached input token rates by 0% compared with uncached input.

What workloads is Qwen 2.5 72B best suited for?

Bilingual CJK/English summarization, structured data extraction, and open-weights deployment.