# Recommended Models - Documentation

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown is available with `Accept: text/markdown` and `.md` URL variants.

Source: /docs/guides/llm-recommended

# Recommended Models

A list of recommended open models for common use cases.

##

[​](#which-open-models-should-i-use)

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.

- Model sizes are marked as Small, Medium, or Large. For MoE models, the activated parameter size is what matters for latency.

- For best latency, use small or medium models. For best quality, use large models or fine-tune medium or small models.

- Model names below are exact model IDs — copy them directly into your API calls. Each links to its model page for live pricing and a playground.

- You can explore all models in the [Novita Model Library](https://novita.ai/models/llm).

###

[​](#code-generation-&-reasoning)

Code generation & reasoning

Model IDSize / NotesContext Window[`moonshotai/kimi-k2.7-code`](https://novita.ai/models/llm/moonshotai-kimi-k2.7-code)Large262K[`zai-org/glm-5.2`](https://novita.ai/models/llm/zai-org-glm-5.2)Large1M[`deepseek/deepseek-v4-pro`](https://novita.ai/models/llm/deepseek-deepseek-v4-pro)Large1M

###

[​](#general-reasoning-&-planning)

General reasoning & planning

Model IDSize / NotesContext Window[`deepseek/deepseek-v4-pro`](https://novita.ai/models/llm/deepseek-deepseek-v4-pro)Large1M[`deepseek/deepseek-v3.2`](https://novita.ai/models/llm/deepseek-deepseek-v3.2)Large160K[`qwen/qwen3.5-397b-a17b`](https://novita.ai/models/llm/qwen-qwen3.5-397b-a17b)Large, 17B active262K

###

[​](#agents-function-calling-&-tool-use)

Agents, function calling & tool use

Model IDSize / NotesContext Window[`zai-org/glm-5.2`](https://novita.ai/models/llm/zai-org-glm-5.2)Large1M[`moonshotai/kimi-k2.7-code`](https://novita.ai/models/llm/moonshotai-kimi-k2.7-code)Large262K[`minimax/minimax-m3`](https://novita.ai/models/llm/minimax-minimax-m3)Large1M

###

[​](#long-context-&-summarization)

Long context & summarization

Model IDSize / NotesContext Window[`zai-org/glm-5.2`](https://novita.ai/models/llm/zai-org-glm-5.2)Large1M[`deepseek/deepseek-v4-pro`](https://novita.ai/models/llm/deepseek-deepseek-v4-pro)Large1M[`deepseek/deepseek-v4-flash`](https://novita.ai/models/llm/deepseek-deepseek-v4-flash)Large, cost-effective1M

###

[​](#vision-&-document-understanding)

Vision & document understanding

Model IDSize / NotesContext Window[`moonshotai/kimi-k2.5`](https://novita.ai/models/llm/moonshotai-kimi-k2.5)Large262K[`qwen/qwen3.5-397b-a17b`](https://novita.ai/models/llm/qwen-qwen3.5-397b-a17b)Large, 17B active262K[`google/gemma-4-31b-it`](https://novita.ai/models/llm/google-gemma-4-31b-it)Medium262K

###

[​](#low-latency-nlu-&-extraction)

Low-latency NLU & extraction

Model IDSize / NotesContext Window[`inclusionai/ling-2.6-flash`](https://novita.ai/models/llm/inclusionai-ling-2.6-flash)MoE, small activation262K[`meta-llama/llama-3.1-8b-instruct`](https://novita.ai/models/llm/meta-llama-llama-3.1-8b-instruct)Small128K[`google/gemma-4-26b-a4b-it`](https://novita.ai/models/llm/google-gemma-4-26b-a4b-it)Medium, 4B active262K

##

[​](#migrating-from-older-models)

Migrating from older models

If you are still calling one of the models below, switch to its recommended replacement:

If you useSwitch to`deepseek/deepseek-r1-0528``deepseek/deepseek-v4-pro``zai-org/glm-4.5``zai-org/glm-5.2``moonshotai/kimi-k2-instruct``moonshotai/kimi-k2.7-code``qwen/qwen3-coder-480b-a35b-instruct``moonshotai/kimi-k2.7-code``meta-llama/llama-4-maverick` / `llama-4-scout`, `qwen/qwen2.5-vl-72b-instruct``moonshotai/kimi-k2.5`, `qwen/qwen3.5-397b-a17b`, or `google/gemma-4-31b-it`

Last modified on July 3, 2026