docs: update recommended models list (#3121)

This commit is contained in:
Aiden Cline
2025-10-12 21:35:31 -05:00
committed by GitHub
parent fd70b9b057
commit 5885b691b9

View File

@@ -33,11 +33,14 @@ There are a lot of models out there, with new models coming out every week.
Consider using one of the models we recommend.
:::
However, there are a only a few of them that are good at both generating code and tool calling.
However, there are only a few of them that are good at both generating code and tool calling.
Here are the ones we recommend with OpenCode:
Here are several models, in no particular order, that work well with OpenCode (to name a few):
- GPT 5
- GPT 5 Codex
- Claude Sonnet 4.5
- Claude Sonnet 4
- Claude Opus 4.1
- Kimi K2
- Qwen3 Coder
@@ -100,7 +103,7 @@ You can globally configure a model's options through the config.
}
```
Here we're configuring global settings for two built-in models: `gpt-5` when accessed via the `openai` provider, and `claude-sonnet-4-20250514` when accessed via the `anthropic` provider.
Here we're configuring global settings for two built-in models: `gpt-5` when accessed via the `openai` provider, and `claude-sonnet-4-20250514` when accessed via the `anthropic` provider.
The built-in provider and model names can be found on [Models.dev](https://models.dev).
You can also configure these options for any agents that you are using. The agent config overrides any global options here. [Learn more](/docs/agents/#additional).
@@ -118,20 +121,20 @@ You can also define custom models that extend built-in ones and can optionally u
"options": {
"reasoningEffort": "high",
"textVerbosity": "low",
"reasoningSummary": "auto"
}
"reasoningSummary": "auto",
},
},
"gpt-5-low": {
"id": "gpt-5",
"options": {
"reasoningEffort": "low",
"textVerbosity": "low",
"reasoningSummary": "auto"
}
}
}
}
}
"reasoningSummary": "auto",
},
},
},
},
},
}
```