Skip to content
CostPerPrompt

Qwen2.5 72B Instruct API Pricing

Alibaba (Qwen) · context window 33K · prices updated 2026-09-15

Input per 1M tokens
$0.36
Output per 1M tokens
$0.4
Cached input per 1M
No discounted cached tier on this model

Where Qwen2.5 72B Instruct sits on price

At $0.4 per million output tokens, Qwen2.5 72B Instruct is a budget tier model — 5.2× cheaper than the median output price of $2.08, which puts it cheaper than 84% and pricier than 16% of the models we track. It sits 11th cheapest of the 53 Alibaba (Qwen) models we track. Output is only 1.1× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.

Output tokens per $1
2,500,000
One full context fill
$0.0118
Cheaper than
84% of tracked models

What real workloads cost on Qwen2.5 72B Instruct

These three workloads are the ones teams actually run on a budget-priced model — a $0.4/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. $0.0002 $912
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0002 $7.20
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0013 $384

Model your exact traffic in the API cost calculator — it preloads Qwen2.5 72B Instruct with caching and batch options.

Qwen2.5 72B Instruct price history

Qwen2.5 72B Instruct's price has not moved since we began tracking it on Aug 2, 2026 — 44 days of stability in a market where 78 of the 334 models we track have repriced over the same period, including 17 of Alibaba (Qwen)'s own 53 models.

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

Qwen2.5 72B Instruct vs DeepSeek V3.2

The closest-priced alternative from another vendor is DeepSeek V3.2 (DeepSeek) — priced within a rounding error on output, with $0.091 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See DeepSeek V3.2 pricing →

Cheaper alternatives

More Alibaba (Qwen) models

Frequently asked questions

How much does the Qwen2.5 72B Instruct API cost?

Qwen2.5 72B Instruct costs $0.36 per million input tokens and $0.4 per million output tokens and no discounted cached-input tier. That works out to roughly 2,500,000 output tokens per dollar.

What does the high-volume classification workload cost on Qwen2.5 72B Instruct?

High-volume classification — 200K requests/day (400 in / 20 out) costs about $0.0002 per request and $912 per month on Qwen2.5 72B Instruct. Short output, huge volume: the input price dominates the bill.

What does it cost to fill Qwen2.5 72B Instruct's 33K context window?

Sending 33K of input in a single request costs $0.0118 at $0.36 per million tokens — before any output. There is no cached-input tier on this model, so every repeat of that context is billed at full price. This is why large context windows are cheap to advertise and expensive to actually use.

Is Qwen2.5 72B Instruct worth the price?

Qwen2.5 72B Instruct is in the cheapest end of the market — cheaper than 84% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.