Qwen
Frontier

Qwen2.5-72B-Instruct

Large

Alibaba's open-weights flagship. Top-tier on multilingual and coding benchmarks among open models.

Qwen2.5-72B-Instruct is a frontier AI model from Qwen. It costs $0.3600 per million input tokens and $0.4000 per million output tokens (blended $0.3720/M), with a 128,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.3600/M
per million input tokens
OUTPUT
$0.4000/M
per million output tokens
BLENDED 70/30
$0.3720/M
unchanged since 3 May
CONTEXT
128,000
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • Top open-weights multilingual
  • Strong code
  • 128K context
  • Permissive license
Typical use cases
  • Multilingual self-hosted chat
  • Code generation
  • Fine-tune base

Benchmarks

vs. best public score
MMLU86.1%
Multitask academic knowledge across 57 subjects. Source: Alibaba (Qwen team) (self-reported), MMLU (5-shot), base model, read 2026-11-10.
Graduate-level science questions, "Google-proof". Source: Alibaba (Qwen team) (self-reported), GPQA, read 2026-11-10.
MATH83.1%
High-school competition math problems. Source: Alibaba (Qwen team) (self-reported), MATH, read 2026-11-10.
HumanEval86.6%
Python function synthesis from docstrings. Source: Alibaba (Qwen team) (self-reported), HumanEval, read 2026-11-10.
LMArena Elo1303 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Qwen

See all 22 →

Frequently asked questions

How much does Qwen2.5-72B-Instruct cost?

Qwen2.5-72B-Instruct costs $0.3600 per million input tokens and $0.4000 per million output tokens, for a blended reference rate of $0.3720 per million tokens.

What is Qwen2.5-72B-Instruct's context window?

Qwen2.5-72B-Instruct supports up to 128,000 tokens of context in a single request.

What is Qwen2.5-72B-Instruct best for?

Qwen2.5-72B-Instruct is well suited to Top open-weights multilingual, Strong code and 128K context.

Who makes Qwen2.5-72B-Instruct?

Qwen2.5-72B-Instruct is developed and served by Qwen.

Terms used on this page