Skip to content
Qwen

Qwen2.5 72B Instruct

Qwen2.5 72B Instruct is a large language model made by Qwen, added to the catalog on 19 Sep 2024. It has a context window of 32,768 tokens and costs $0.36 per 1M input tokens and $0.40 per 1M output tokens. It accepts text and produces text. Typical uses: generate detailed long-form content, enhance chatbot interactions and support multilingual communication.

Price checked ยท source: OpenRouter

What Qwen2.5 72B Instruct is

Qwen2.5 72B Instruct, released by Qwen on September 19, 2024, is a large language model designed to handle complex text-based tasks. With a context window of up to 128K tokens, it excels in generating both short and long texts, understanding structured data, and providing structured outputs like JSON. The model supports multilingual capabilities in over 29 languages, making it versatile for various applications. It also features improved instruction following and enhanced role-play implementation, benefiting chatbots and interactive systems. Input and output are text-based, with a range of parameters available for customization.

Key features

  • 128K token context window
  • Multilingual support in 29 languages
  • Enhanced instruction following
  • Structured data understanding
  • Generates structured outputs
  • Improved role-play capabilities

Typical uses

  • Generate detailed long-form content
  • Enhance chatbot interactions
  • Support multilingual communication
  • Understand and output structured data
  • Facilitate coding and math tasks

Qwen2.5 72B Instruct pricing

US dollars, list price through OpenRouter.

Checked
Qwen2.5 72B Instruct price list
ItemStandard
Input, per 1M tokens$0.36
Output, per 1M tokens$0.40

No price change since it was added on 19 Sep 2024.

What typical tasks cost with Qwen2.5 72B Instruct
What a task costsCost
Answer a short question500 in / 300 out$0.0003
Summarise a 50-page PDF25,000 in / 800 out$0.0093
Review a 2,000-line source file30,000 in / 2,000 out$0.012
Read a 300-page contract set150,000 in / 1,500 out$0.055
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

Qwen2.5 72B Instruct specifications

Qwen2.5 72B Instruct limits and identity
Model idqwen/qwen-2.5-72b-instruct
Versionqwen-2.5-72b-instruct
Context window32,768 tokensAbout 24,576 English words
Max output16,384 tokens
Knowledge cutoff2024-06-30
Added to catalog19 Sep 2024
Qwen2.5 72B Instruct capabilities
Input typestext
Output typestext
Tool callingYes
Structured outputsYes
Reasoning effort controlNo
Content moderationNot applied by provider

Sample outputs

The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.

Write a short essay

RUN20 Nov 2026
Prompt

Write 150 words on how AI might positively upend work, leisure and creativity

Output

Artificial Intelligence (AI) has the potential to positively transform work, leisure, and creativity in profound ways. In the workplace, AI can automate mundane and repetitive tasks, freeing up human employees to focus on more strategic and creative endeavors. This not only increases productivity but also enhances job satisfaction by allowing workers to engage in more meaningful and fulfilling tasks. For instance, AI can handle data entry, scheduling, and even customer service, enabling professionals to concentrate on innovation and problem-solving. In the realm of leisure, AI can personalize entertainment experiences, tailoring content to individual preferences and moods. Smart home devices and AI-driven recommendation systems can create customized playlists, suggest movies, and even plan activities, making leisure time more enjoyable and enriching. Additionally, AI can facilitate new forms of social interaction, such as virtual reality experiences and online communities, connecting people with shared interests from around the world. Creatively, AI can be a powerful tool for artists, writers, and designers. It can generate ideas, assist in the creative process, and even produce original works of art. For example, AI can help musicians compose music, writers generate story ideas, and artists create visual designs. This collaboration between human creativity and AI can lead to innovative and groundbreaking works that might not have been possible otherwise. Overall, AI has the potential to enhance and expand the boundaries of human potential in work, leisure, and creativity.

Compare Qwen2.5 72B Instruct

Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.

Qwen2.5 72B Instruct questions

How much does Qwen2.5 72B Instruct cost?

Qwen2.5 72B Instruct costs $0.36 per 1M input tokens and $0.40 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.0093.

What is the context window of Qwen2.5 72B Instruct?

32,768 tokens, or roughly 24,576 English words. It can write up to 16,384 tokens in one response.

Can Qwen2.5 72B Instruct read images and PDFs?

No. It accepts text only. It produces text, so it cannot generate images.

How do I try Qwen2.5 72B Instruct?

Use the "Try Qwen2.5 72B Instruct" button on this page. It opens the chat with Qwen2.5 72B Instruct selected; you type the question and press send.

Try Qwen2.5 72B Instruct on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.