LLM Pricing

← All Models

Qwen2.5 72B Instruct

🇨🇳 Qwen (Alibaba) · Qwen2.5 72B

Input Price — per million tokens
Output Price — per million tokens
Context Window 33K tokens Output limit: 16K
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

Qwen2.5 72B Instruct is a large language model API from Qwen (Alibaba), part of its Qwen2.5 72B model family. The 33K-token context window — around 49 pages of text — comfortably handles long documents, multi-file code, or extended conversations. On Artificial Analysis's Intelligence Index it scores 9 (F grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.

Dimension Unit Price (USD) Price (TWD) Effective From
No pricing data yet

Provider
通義千問（阿里） (Qwen (Alibaba))
Model Family
Qwen2.5 72B
Version String
qwen/qwen-2.5-72b-instruct
Status
Active
Modality
Text
Context Window
32,768 tokens
Output Limit
16,384 tokens

Index Metrics

Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis

Intelligence Index 9 F Measured: 2026-08-29

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 20.0% F Measured: 2026-08-29
GPQA Diamond 49.1% C Measured: 2026-08-29
HLE 3.6% D Measured: 2026-08-29
IFBench 36.9% D Measured: 2026-08-29
Non-Hallucination 14.5% Measured: 2026-08-29
Omniscience Accuracy 17.5% Measured: 2026-08-29
SciCode 26.7% C Measured: 2026-08-29
Tau2 34.5% Measured: 2026-08-29
TerminalBench 4.5% Measured: 2026-08-29

Use Case Analysis

Model strengths, weaknesses, and ideal use cases based on benchmarks and official documentation

Strength

  • General Knowledge MMLU 86.1%, MMLU-Redux 86.8%, strong general knowledge performance. Benchmark
  • Math Reasoning MATH 83.1%, GSM8K 95.8%, excellent mathematical problem-solving. Benchmark
  • Multilingual Support Strong performance across multiple languages including Chinese. Official

Best For

  • General Purpose Tasks Balanced performance across knowledge, coding, and reasoning tasks. Official
  • Mathematical Applications MATH score 83.1% ideal for mathematical problem-solving. Benchmark

90-Day Price Trend

Input / Output price (USD per 1M tokens)

Past 90 days of records; every price change is shown here

Date Dimension Price (USD) Source
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter
Output $0.400 OpenRouter
Input $0.360 OpenRouter

Key Insights

Key data points from this page for quick reference and citation.

  • Context window: 32,768 tokens
  • Provider: Qwen (Alibaba)
  • Model family: Qwen2.5 72B
  • Modalities: Text
  • Data source: OpenRouter, updated daily