Qwen2-72B

AlibabaOpen weights

Qwen2-72B by Alibaba costs — per 1M input tokens and — per 1M output tokens, with a —-token context window.

Pricing

Input (per 1M tokens)

—

Output (per 1M tokens)

—

Cached input (per 1M)

—

Specifications

Provider: Alibaba
Context window: —
Parameters: 73B
Released: Jun 2024
Open weights: Yes
Frontier model: No

Benchmarks

Epoch Capabilities Index: 125.3

Compare Qwen2-72B with…

Qwen2-72B vs DeepSeek V3.1 Terminus$1.00/1M Qwen2-72B vs Qwen2.5 Coder 32B Instruct$1.00/1M Qwen2-72B vs Nemotron 3 Super 120B A12B$1.00/1M Qwen2-72B vs MiniMax M2$1.02/1M Qwen2-72B vs MiniMax M2.5$0.95/1M Qwen2-72B vs DeepSeek V3.1$0.95/1M

FAQ

How much does Qwen2-72B cost?

Qwen2-72B is priced at — per 1M input tokens and — per 1M output tokens. Output tokens cost more than input.

What is Qwen2-72B's context window?

Qwen2-72B supports a context window of — tokens — the maximum prompt plus response length it can handle in a single request.

Is Qwen2-72B open weight?

Yes — Qwen2-72B has openly available weights.

Data as of 2026-10-16. Source: Epoch AI, Data on AI Models (CC BY 4.0), epoch.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.