HHostingByteSoftware
Ctrl K
ComunidadGuías…

docs/customize/models.mdx

Rama main · réplica de lectura del repositorio original.

Archivo original ↗Preguntar a KiBot
---
title: "Models"
description: "Models form the foundation of the entire agent experience, offering different specialized capabilities:"
---

import { ModelRecommendations } from "/snippets/ModelRecommendations.jsx";

- **[Chat](/customize/model-roles/chat)**: Power conversational interactions about code and provide detailed guidance
- **[Edit](/customize/model-roles/edit)**: Handle complex code transformations and refactoring tasks
- **[Apply](/customize/model-roles/apply)**: Execute targeted code modifications with high accuracy
- **[Autocomplete](/customize/model-roles/autocomplete)**: Provide real-time suggestions as developers type
- **[Embedding](/customize/model-roles/embeddings)**: Transform code into vector representations for semantic search
- **[Reranker](/customize/model-roles/reranking)**: Improve search relevance by ordering results based on semantic meaning


## Recommended Models

### Best Models by Role

<ModelRecommendations role="all" />


## Learn More About Models

Continue supports [many model providers](/customize/model-providers/top-level/openai), including Anthropic, OpenAI, Gemini, Ollama, Amazon Bedrock, Azure, xAI, and more. Models can have various roles like `chat`, `edit`, `apply`, `autocomplete`, `embed`, and `rerank`.

Read more about [model roles](/customize/model-roles), [model capabilities](/customize/deep-dives/model-capabilities) and view [`models`](/reference#models) in the YAML Reference.

### Example Model Setup Instructions

# Frontier Models

[Claude Sonnet 4.6](https://continue.dev/anthropic/claude-sonnet-4-6) from Anthropic

1. Get your API key from [Anthropic](https://console.anthropic.com/)
2. Add [Claude Sonnet 4.6](https://continue.dev/anthropic/claude-sonnet-4-6) to your Continue config
3. Add `ANTHROPIC_API_KEY` to your environment or config
4. Click `Reload config` in the config selector in the Continue IDE extension

[Qwen Coder 3 480B](https://continue.dev/openrouter/qwen3-coder) from Qwen

1. Get your API key from [OpenRouter](https://openrouter.ai/settings/keys)
2. Add [Qwen Coder 3 480B](https://continue.dev/openrouter/qwen3-coder)  your Continue config
3. Add `OPENROUTER_API_KEY` to your environment or config
4. Click `Reload config` in the config selector in the Continue IDE extension

[GPT-5](https://continue.dev/openai/gpt-5) from OpenAI

1. Get your API key from [OpenAI](https://platform.openai.com)
2. Add [GPT-5](https://continue.dev/openai/gpt-5)  your Continue config
3. Add `OPENAI_API_KEY` to your environment or config
4. Click `Reload config` in the config selector in the Continue IDE extension

[Kimi K2](https://continue.dev/openrouter/kimi-k2) from Moonshot AI

1. Get your API key from [OpenRouter](https://openrouter.ai/settings/keys)
2. Add [Kimi K2](https://continue.dev/openrouter/kimi-k2)  your Continue config
3. Add `OPENROUTER_API_KEY` to your environment or config
4. Click `Reload config` in the config selector in the Continue IDE extension

[Gemini 3.1 Pro](https://continue.dev/google/gemini-3.1-pro-preview) from Google

1. Get your API key from [Google AI Studio](https://aistudio.google.com)
2. Add [Gemini 3.1 Pro](https://continue.dev/google/gemini-3.1-pro-preview)  your Continue config
3. Add `GEMINI_API_KEY` to your environment or config
4. Click `Reload config` in the config selector in the Continue IDE extension

[Grok Code Fast 1](https://continue.dev/xai/grok-code-fast-1) from xAI

1. Get your API key from [xAI](https://console.x.ai/)
2. Add [Grok Code Fast 1](https://continue.dev/xai/grok-code-fast-1)  your Continue config
3. Add `XAI_API_KEY` to your environment or config
4. Click `Reload config` in the config selector in the Continue IDE extension

[Devstral Medium](https://continue.dev/mistral/devstral-medium) from Mistral AI

1. Get your API key from [Mistral AI](https://console.mistral.ai/)
2. Add [Devstral Medium](https://continue.dev/mistral/devstral-medium)  your Continue config
3. Add `MISTRAL_API_KEY` to your environment or config
4. Click `Reload config` in the config selector in the Continue IDE extension

[gpt-oss-120b](https://continue.dev/openrouter/gpt-oss-120b) from OpenAI

1. Get your API key from [OpenRouter](https://openrouter.ai/settings/keys)
2. Add [gpt-oss-120b](https://continue.dev/openrouter/gpt-oss-120b)  your Continue config
3. Add `OPENROUTER_API_KEY` to your environment or config
4. Click `Reload config` in the config selector in the Continue IDE extension

### Local Models

<Info>
Need a quick setup walkthrough? Check out [Using Ollama with Continue: A Developer's Guide](https://docs.continue.dev/guides/ollama-guide).
</Info>

These models can be run on your computer if you have enough VRAM.

Their limited tool calling and reasoning capabilities will make it challenging to use agent mode.

[Qwen3 Coder 30B](https://continue.dev/ollama/qwen3-coder-30b)

1. Add [Qwen3 Coder 30B](https://continue.dev/ollama/qwen3-coder-30b)  your Continue config
2. Run the model with [Ollama](https://docs.continue.dev/guides/ollama-guide#using-ollama-with-continue-a-developers-guide)
3. Click `Reload config` in the config selector in the Continue IDE extension

[gpt-oss-20b](https://continue.dev/ollama/gpt-oss-20b)

1. Add [gpt-oss-20b](https://continue.dev/ollama/gpt-oss-20b)  your Continue config
2. Run the model with [Ollama](https://docs.continue.dev/guides/ollama-guide#using-ollama-with-continue-a-developers-guide)
3. Click `Reload config` in the config selector in the Continue IDE extension

[Devstral Small 27B](https://continue.dev/ollama/devstral)

1. Add [Devstral Small](https://continue.dev/ollama/devstral)  your Continue config
2. Run the model with [Ollama](https://docs.continue.dev/guides/ollama-guide#using-ollama-with-continue-a-developers-guide)
3. Click `Reload config` in the config selector in the Continue IDE extension

[Qwen2.5-Coder 7B](https://continue.dev/ollama/qwen2.5-coder-7b) from Qwen

1. Add [Qwen2.5-Coder 7B](https://continue.dev/ollama/qwen2.5-coder-7b)  your Continue config
2. Run the model with [Ollama](https://docs.continue.dev/guides/ollama-guide#using-ollama-with-continue-a-developers-guide)
3. Click `Reload config` in the config selector in the Continue IDE extension

[Gemma 3 4B](https://continue.dev/ollama/gemma3-4b) from Google

1. Add [Gemma 3 4B](https://continue.dev/ollama/gemma3-4b)  your Continue config
2. Run the model with [Ollama](https://docs.continue.dev/guides/ollama-guide#using-ollama-with-continue-a-developers-guide)
3. Click `Reload config` in the config selector in the Continue IDE extension

[Qwen2.5-Coder 1.5B](https://continue.dev/ollama/qwen2.5-coder-1.5b) from Qwen

1. Add [Qwen2.5-Coder 1.5B](https://continue.dev/ollama/qwen2.5-coder-1.5b)  your Continue config
2. Run the model with [Ollama](https://docs.continue.dev/guides/ollama-guide#using-ollama-with-continue-a-developers-guide)
3. Click `Reload config` in the config selector in the Continue IDE extension