mirror of
https://github.com/Aider-AI/aider.git
synced 2025-05-25 14:55:00 +00:00
57 lines
1.8 KiB
Markdown
57 lines
1.8 KiB
Markdown
---
|
|
title: Connecting to LLMs
|
|
nav_order: 40
|
|
has_children: true
|
|
description: Aider can connect to most LLMs for AI pair programming.
|
|
---
|
|
|
|
# Aider can connect to most LLMs
|
|
{: .no_toc }
|
|
|
|
[](https://aider.chat/assets/llms.jpg)
|
|
|
|
|
|
## Best models
|
|
{: .no_toc }
|
|
|
|
Aider works best with these models, which are skilled at editing code:
|
|
|
|
- [GPT-4o](/docs/llms/openai.html)
|
|
- [Claude 3.5 Sonnet](/docs/llms/anthropic.html)
|
|
- [Claude 3 Opus](/docs/llms/anthropic.html)
|
|
- [DeepSeek Coder V2](/docs/llms/deepseek.html)
|
|
|
|
|
|
## Free models
|
|
{: .no_toc }
|
|
|
|
Aider works with a number of **free** API providers:
|
|
|
|
- The [DeepSeek Coder V2](/docs/llms/deepseek.html) model gets the top score on aider's code editing benchmark. DeepSeek has been offering 5M free tokens of API usage.
|
|
- Google's [Gemini 1.5 Pro](/docs/llms/gemini.html) works with aider, with
|
|
code editing capabilities similar to GPT-3.5.
|
|
- You can use [Llama 3 70B on Groq](/docs/llms/groq.html) which is comparable to GPT-3.5 in code editing performance.
|
|
- Cohere also offers free API access to their [Command-R+ model](/docs/llms/cohere.html), which works with aider as a *very basic* coding assistant.
|
|
|
|
## Local models
|
|
{: .no_toc }
|
|
|
|
Aider can work also with local models, for example using [Ollama](/docs/llms/ollama.html).
|
|
It can also access
|
|
local models that provide an
|
|
[Open AI compatible API](/docs/llms/openai-compat.html).
|
|
|
|
## Use a capable model
|
|
{: .no_toc }
|
|
|
|
Check
|
|
[Aider's LLM leaderboards](https://aider.chat/docs/leaderboards/)
|
|
to see which models work best with aider.
|
|
|
|
Be aware that aider may not work well with less capable models.
|
|
If you see the model returning code, but aider isn't able to edit your files
|
|
and commit the changes...
|
|
this is usually because the model isn't capable of properly
|
|
returning "code edits".
|
|
Models weaker than GPT 3.5 may have problems working well with aider.
|
|
|