# Models Overview

Arcee AI offers models at various sizes to meet different deployment scenarios. Choosing the right model can help you complete tasks more efficiently, accurately, and cost effectively. 

### Models

To help you find the best fit for your use case, we’ve created a table outlining the core features and strengths of each model in the Arcee AI family. Note that API hosted models are always the lastest update. Previous versions and post-trains are available for download on HuggingFace.

| Model                 | Trinity-Nano-6B                                                                                                                                                                                                                                                                                              | Trinity-Mini-26B                                                                                                                                                                                                                  | Trinity \[Coming Soon] |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------- |
| **Strength**          | Lightweight, ultra-low latency model.                                                                                                                                                                                                                                                                        | Fast and cost-efficient model for well-defined tasks.                                                                                                                                                                             | Coming Soon            |
| **Ideal Deployment**  | Fully local on consumer GPUs, edge servers, and mobile devices. Tuned for offline operation.                                                                                                                                                                                                                 | Serve customer-facing apps, agent backends, and high-throughput services in your cloud or VPC.                                                                                                                                    | Coming Soon            |
| **Active Parameters** | 1B per token                                                                                                                                                                                                                                                                                                 | 3B per token                                                                                                                                                                                                                      | Coming Soon            |
| **Context Window**    | 128k tokens                                                                                                                                                                                                                                                                                                  | 128k tokens                                                                                                                                                                                                                       | Coming Soon            |
| **Reasoning Support** | Yes                                                                                                                                                                                                                                                                                                          | Yes                                                                                                                                                                                                                               | Coming Soon            |
| **Knowledge Cutoff**  | 2024                                                                                                                                                                                                                                                                                                         | 2024                                                                                                                                                                                                                              | Coming Soon            |
| **Intelligence**      | <p><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><br>Efficient</p>                                                                                                                                             | <p><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><span data-gb-custom-inline data-tag="emoji" data-code="2b50">⭐</span><br>Good</p> | Coming Soon            |
| **Speed**             | <p><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><br>Very Fast</p> | <p><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><span data-gb-custom-inline data-tag="emoji" data-code="26a1">⚡</span><br>Fast</p> | Coming Soon            |
| **Max Output Tokens** | <p>non-reasoning: 8k<br>reasoning: 32k</p>                                                                                                                                                                                                                                                                   | <p>non-reasoning: 8k<br>readoning: 32k</p>                                                                                                                                                                                        | Coming Soon            |
| **Endpoints**         | Chat Completion                                                                                                                                                                                                                                                                                              | Chat Completion                                                                                                                                                                                                                   | Coming Soon            |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.arcee.ai/~/revisions/UOfL3qIelQCFUdc2TpQu/get-started/models-overview.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.