> ## Documentation Index
> Fetch the complete documentation index at: https://novita.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

#    Recommended Models

A list of recommended open models for common use cases.

## Which open models should I use?

Actually, there’s no single right answer! Here’s a curated list based on Novita internal testing, community feedback, and external benchmarks. We recommend using it as a starting point, and we will update it regularly as new models emerge.

<Note>
  * Model sizes are marked as Small, Medium, or Large
  * For best latency, use small or medium models. For best quality, use large models or fine-tune medium or small models.
  * You can explore all models in the Novita Model Library
</Note>

| **Use Cases**                       | **Recommended Models**                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
| ----------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Code generation & reasoning**     | [**Deepseek-r1-0528**](https://novita.ai/models/llm/deepseek-deepseek-r1-0528), [**Deepseek-v3-0324**](https://novita.ai/models/llm/deepseek-deepseek-v3-0324),[**Qwen3-Coder-480B-A35B-Instruct**](https://novita.ai/models/llm/qwen-qwen3-coder-480b-a35b-instruct)[**,Qwen3-235B-A22B-Instruct-2507**](https://novita.ai/models/llm/qwen-qwen3-235b-a22b-instruct-2507)\_(Large)                               \_[**Kimi-K2-Instruct**](https://novita.ai/models/llm/moonshotai-kimi-k2-instruct)[**,GLM-4.5**](https://novita.ai/models/llm/zai-org-glm-4.5)(Medium) |
| **General reasoning & planning**    | [**Deepseek-r1-0528**](https://novita.ai/models/llm/deepseek-deepseek-r1-0528), [**Deepseek-v3-0324**](https://novita.ai/models/llm/deepseek-deepseek-v3-0324) *(Large)*<br />[**Qwen-2.5-72b-instruct**](https://novita.ai/models/llm/qwen-qwen-2.5-72b-instruct), [**Llama-3.3-70b-instruct**](https://novita.ai/models/llm/meta-llama-llama-3.3-70b-instruct) *(Medium)*                                                                                                                                                                                              |
| **Function calling & tool use**     | [**Qwen3-235b-a22b-fp8**](https://novita.ai/models/llm/qwen-qwen3-235b-a22b-fp8) *(Large)*<br />**Qwen 3 Family Models** *(Large/Medium/Small)*                                                                                                                                                                                                                                                                                                                                                                                                                          |
| **Long context & summarization**    | [**Llama-4-maverick-17b-128e-instruct-fp8**](https://novita.ai/models/llm/meta-llama-llama-4-maverick-17b-128e-instruct-fp8) *(Large)*<br />[**Llama-4-scout-17b-16e-instruct**](https://novita.ai/models/llm/meta-llama-llama-4-scout-17b-16e-instruct) *(Medium)*                                                                                                                                                                                                                                                                                                      |
| **Vision & document understanding** | [**Llama-4-maverick-17b-128e-instruct-fp8**](https://novita.ai/models/llm/meta-llama-llama-4-maverick-17b-128e-instruct-fp8) *(Large)*<br />[**Qwen2.5-vl-72b-instruct**](https://novita.ai/models/llm/qwen-qwen2.5-vl-72b-instruct), [**Llama-4-scout-17b-16e-instruct**](https://novita.ai/models/llm/meta-llama-llama-4-scout-17b-16e-instruct) *(Medium)*                                                                                                                                                                                                            |
| **Low-latency NLU & extraction**    | [**Llama-3.1-8b-instruct**](https://novita.ai/models/llm/meta-llama-llama-3.1-8b-instruct), [**Llama-3.2-3b-instruct**](https://novita.ai/models/llm/meta-llama-llama-3.2-3b-instruct), [**Llama-3.2-1b-instruct**](https://novita.ai/models/llm/meta-llama-llama-3.2-1b-instruct) *(Small)*                                                                                                                                                                                                                                                                             |

*Last updated: August 1, 2025*