Skip to content
Mistral

Mistral Nemo

Mistral Nemo is a large language model made by Mistral, added to the catalog on 19 Jul 2024. It has a context window of 131,072 tokens and costs $0.029 per 1M input tokens and $0.03 per 1M output tokens. It accepts text and produces text. Typical uses: generate multilingual text outputs, enhance text-based applications and experiment with large context tasks.

Price checked ยท source: OpenRouter

What Mistral Nemo is

Mistral Nemo, developed by Mistralai in partnership with NVIDIA, is a 12 billion parameter model released on July 19, 2024. Designed for text-to-text tasks, it offers a substantial 128k token context window, making it versatile for various applications. The model supports multiple languages, including English, French, and Chinese, and is equipped with function calling capabilities. It operates under the Apache 2.0 license, ensuring flexibility in use. With a range of parameters like frequency_penalty and temperature, users can fine-tune outputs to meet specific needs.

Key features

  • 12 billion parameter model
  • 128k token context length
  • Multilingual support
  • Function calling capabilities
  • Apache 2.0 license

Typical uses

  • Generate multilingual text outputs
  • Enhance text-based applications
  • Experiment with large context tasks
  • Fine-tune outputs with various parameters

Mistral Nemo pricing

US dollars, list price through OpenRouter.

Checked
Mistral Nemo price list
ItemStandard
Input, per 1M tokens$0.029
Output, per 1M tokens$0.03

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

What typical tasks cost with Mistral Nemo
What a task costsCost
Answer a short question500 in / 300 out$0.0000
Summarise a 50-page PDF25,000 in / 800 out$0.0007
Review a 2,000-line source file30,000 in / 2,000 out$0.0009
Read a 300-page contract set150,000 in / 1,500 out$0.0044
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.

Mistral Nemo specifications

Mistral Nemo limits and identity
Model idmistralai/mistral-nemo
Versionmistral-nemo
Context window131,072 tokensAbout 98,304 English words
Max output16,384 tokens
Knowledge cutoff2024-04-30
Added to catalog19 Jul 2024
Mistral Nemo 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

AI has the potential to significantly transform work, leisure, and creativity in positive ways. Here's how: 1. **Work**: AI can automate repetitive tasks, freeing up human time for creative, strategic, and interpersonal work. It can provide real-time data analysis, enabling better decision-making. AI-driven tools can also personalize learning experiences, helping workers upskill and reskill continuously. 2. **Leisure**: AI can curate personalized entertainment experiences, recommending movies, music, or games tailored to individual tastes. It can also facilitate virtual travel experiences, allowing people to explore the world from their homes. In healthcare, AI can help manage stress and mental health, promoting well-being. 3. **Creativity**: AI can be a powerful creative collaborator. It can generate new ideas, suggest variations, and even complete unfinished work. In art, AI has created masterpieces, and in music, it has composed symphonies. AI can also democratize creativity by making tools more accessible, like using natural language processing to help write stories or create poetry. However, it's crucial to ensure these advancements are equitable and beneficial to all, with proper safeguards against job displacement, data privacy concerns, and algorithmic biases.

Mistral Nemo questions

How much does Mistral Nemo cost?

Mistral Nemo costs $0.029 per 1M input tokens and $0.03 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.0007.

What is the context window of Mistral Nemo?

131,072 tokens, or roughly 98,304 English words. It can write up to 16,384 tokens in one response.

Can Mistral Nemo read images and PDFs?

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

How do I try Mistral Nemo?

Use the "Try Mistral Nemo" button on this page. It opens the chat with Mistral Nemo selected; you type the question and press send.

Try Mistral Nemo 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.