Mistral AI: Mistral Nemo 12B

This model is no longer available.

Add AI to your application with Puter.js.

Explore Other Models

Model Card

Mistral Nemo 12B is a 12B parameter model developed in collaboration with NVIDIA, released under Apache 2.0 with a 128K context window.

It uses the Tekken tokenizer trained on 100+ languages, which compresses source code and multilingual text ~30% more efficiently than previous Mistral tokenizers. Mistral Nemo 12B is state-of-the-art in its size category for reasoning, world knowledge, and coding, significantly outperforming Mistral 7B on instruction following, multi-turn conversations, and code generation.

Benchmark scores include 68.0% on MMLU (5-shot), 83.5% on HellaSwag, and 76.8% on Winogrande. It supports function calling and is an ideal drop-in replacement for Mistral 7B where stronger multilingual and reasoning capabilities are needed.

Context Window 128K

tokens

Max Output 128K

tokens

Input Cost $0.15

per million tokens

Output Cost $0.15

per million tokens

Input text

modalities

Tool Use Yes

Knowledge Cutoff Jul 2024

Release Date Jul 25, 2024

Code Example

Add AI to your app with the Puter.js AI API, no API keys or setup required.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms").then(response => {
    document.body.innerHTML = response.message.content;
});

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms").then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

More AI Models From Mistral AI

Find other Mistral AI models →

Chat

Mistral Medium 3.5

Mistral Medium 3.5 is a dense 128-billion-parameter multimodal model from Mistral AI that unifies instruction-following, reasoning, and coding into a single set of weights. It features a 256k-token context window, native function calling, structured JSON output, and vision capabilities via a custom-trained encoder that handles variable image sizes. A per-request reasoning_effort parameter lets you toggle between fast responses and deeper chain-of-thought processing, making the same model suitable for quick chat replies and complex agentic workflows. On benchmarks, it scores 77.6% on SWE-Bench Verified and 91.4% on τ³-Telecom. It replaces Mistral's previous Medium 3.1, Magistral, and Devstral 2 models. Priced at $1.50 per million input tokens and $7.50 per million output tokens, it's a strong fit for developers building tool-calling agents, long-horizon coding tasks, and multi-step automation pipelines.

Chat

Mistral Medium 3.5

Mistral Medium 3.5 is a dense 128-billion-parameter multimodal model from Mistral AI that unifies instruction-following, reasoning, and coding into a single set of weights. This entry is Mistral's own dated direct-integration id for the same release available as mistralai/mistral-medium-3-5 through OpenRouter. It features a 256k-token context window, native function calling, structured JSON output, and vision capabilities via a custom-trained encoder that handles variable image sizes. A per-request reasoning_effort parameter lets you toggle between fast responses and deeper chain-of-thought processing, making the same model suitable for quick chat replies and complex agentic workflows. On benchmarks, it scores 77.6% on SWE-Bench Verified and 91.4% on τ³-Telecom. It replaces Mistral's previous Medium 3.1, Magistral, and Devstral 2 models. Priced at $1.50 per million input tokens and $7.50 per million output tokens, it's a strong fit for developers building tool-calling agents, long-horizon coding tasks, and multi-step automation pipelines.

Chat

Mistral Small 4

Mistral Small 4 is a 119B-parameter open-source Mixture-of-Experts model (6B active per token) released under Apache 2.0, unifying instruction-following, reasoning, multimodal (text + image), and agentic coding into a single deployment. It features 128 experts, a 256k context window, and configurable reasoning effort that lets developers toggle between fast responses and deep step-by-step reasoning per request. Compared to its predecessor Mistral Small 3, it delivers 40% lower latency and 3x higher throughput while matching or surpassing GPT-OSS 120B on key benchmarks.

Frequently Asked Questions

How do I use Mistral Nemo 12B?

Mistral Nemo 12B is no longer available through Puter.js. Explore other AI models for alternatives.

What is the pricing for Mistral Nemo 12B?

Mistral Nemo 12B costs $0.15 per 1M input tokens and $0.15 per 1M output tokens.

	Price per 1M tokens
Input	$0.15
Output	$0.15

Who created Mistral Nemo 12B?

Mistral Nemo 12B was created by Mistral AI and released on Jul 25, 2024.

What is the context window of Mistral Nemo 12B?

Mistral Nemo 12B supports a context window of 128K tokens. For reference, that is roughly equivalent to 256 pages of text.

What is the max output length of Mistral Nemo 12B?

Mistral Nemo 12B can generate up to 128K tokens in a single response.

What is the knowledge cutoff of Mistral Nemo 12B?

Mistral Nemo 12B has a knowledge cutoff date of Jul 2024. This means the model was trained on data available up to that date.

What types of input can Mistral Nemo 12B process?

Mistral Nemo 12B accepts the following input types: text. It produces: text.

Does Mistral Nemo 12B support tool use (function calling)?

Yes, Mistral Nemo 12B supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Mistral Nemo 12B API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add AI to your application without worrying about API keys or setup.

Explore Models View Tutorials