Nous Research: DeepHermes 3 Mistral 24B Preview
This model is no longer available.Add AI to your application with Puter.js.
Explore Other ModelsModel Card
DeepHermes 3 Mistral 24B Preview is a 24B parameter instruction-tuned model based on Mistral-Small-24B, featuring a dual-mode system that toggles between intuitive chat responses and deep reasoning mode with extended chains of thought. It excels at function calling, structured JSON outputs, and multi-turn reasoning with the ability to use up to 13,000 tokens for complex problems.
Context Window N/A
tokens
Max Output 33K
tokens
Input Cost $0.02
per million tokens
Output Cost $0.1
per million tokens
Release Date Mar 2, 2025
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 Nous Research
Find other Nous Research models →
Hermes 4 14B
Hermes 4 14B is the smallest model in Nous Research's Hermes 4 family, a fine-tune of Qwen3-14B trained on a post-training corpus of roughly 60B tokens built around verified reasoning traces. It is a hybrid reasoning model. It answers directly by default and can be switched into a reasoning mode that works through explicit think segments before the final answer, with training aimed at keeping those reasoning traces from running overlong. It is trained for function calling and tool use within a single assistant turn, and for structured outputs, including emitting schema-valid JSON and repairing malformed objects. In line with the Hermes series' focus on steerability and neutral alignment, Nous Research reports state-of-the-art results for Hermes 4 on its RefusalBench test, meaning fewer refused requests than comparable models.
ChatHermes 4 405B
Hermes 4 405B is a frontier hybrid-mode reasoning model based on Llama-3.1-405B, trained on a 60B token dataset with verified reasoning traces. It features toggleable deep reasoning via think tags, massive improvements in math, code, STEM, and logic, and achieves state-of-the-art on RefusalBench for reduced censorship.
ChatHermes 3 70B Instruct
Hermes 3 Llama 3.1 70B is a 70B parameter fine-tune of Llama-3.1-70B offering advanced agentic capabilities, improved roleplaying, reasoning, and multi-turn conversation. It provides reliable function calling and structured outputs while being competitive with Llama-3.1 Instruct models at a more accessible size.
Frequently Asked Questions
DeepHermes 3 Mistral 24B Preview is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0.02 |
| Output | $0.1 |
DeepHermes 3 Mistral 24B Preview was created by Nous Research and released on Mar 2, 2025.
DeepHermes 3 Mistral 24B Preview can generate up to 33K tokens in a single response.
DeepHermes 3 Mistral 24B Preview scores 6.1 on the Artificial Analysis Intelligence Index, outperforming 15% of tracked models.
Yes — the DeepHermes 3 Mistral 24B Preview 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