Models

Models form the foundation of the entire agent experience, offering different specialized capabilities:

• Chat: Power conversational interactions about code and provide detailed guidance
• Edit: Handle complex code transformations and refactoring tasks
• Apply: Execute targeted code modifications with high accuracy
• Autocomplete: Provide real-time suggestions as developers type
• Embedding: Transform code into vector representations for semantic search
• Reranker: Improve search relevance by ordering results based on semantic meaning

Recommended Models

Best Models by Role

Model role	Best open models	Best closed models	Notes
Agent Plan	Qwen3 Coder (480B) Qwen3 Coder (30B) Devstral (27B) Kimi K2 (1T) gpt-oss (120B) gpt-oss (20B) GLM 4.5 (355B) GLM 4.5 Air (106B)	Claude Opus 4.1 Claude Sonnet 4 GPT-5 Gemini 2.5 Pro	Closed models are slightly better than open models
Chat Edit	Qwen3 Coder (480B) Qwen3 Coder (30B) gpt-oss (120B) gpt-oss (20B)	Claude Opus 4.1 Claude Sonnet 4 GPT-5 Gemini 2.5 Pro	Closed and open models have pretty similar performance
Autocomplete	QwenCoder2.5 (1.5B) QwenCoder2.5 (7B)	Codestral Mercury Coder	Closed models are slightly better than open models
Apply	N/A	Relace Instant Apply Morph Fast Apply	Open models are not good enough for this model role
Embed	Nomic Embed Text Qwen3 Embedding	Voyage Code 3 Morph Embeddings Codestral Embed	Closed models are slightly better than open models
Rerank	zerank-1 zerank-1-small Qwen3 Reranker	Voyage Rerank 2.5 Relace Code Rerank Morph Rerank	Open models are beginning to emerge for this model role
Next Edit	Instinct	Mercury Coder	Closed models are better than open models

Learn More About Models

Continue supports many model providers, 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, model capabilities and view models in the YAML Reference.

Example Model Setup Instructions

Frontier Models

Claude 4 Sonnet from Anthropic

1. Get your API key from Anthropic
2. Add Claude 4 Sonnet to an agent on Continue Hub
3. Add ANTHROPIC_API_KEY as a User Secret on Continue Hub here
4. Click Reload config in the agent selector in the Continue IDE extension

Qwen Coder 3 480B from Qwen

1. Get your API key from OpenRouter
2. Add Qwen Coder 3 480B to an agent on Continue Hub
3. Add OPENROUTER_API_KEY as a User Secret on Continue Hub here
4. Click Reload config in the agent selector in the Continue IDE extension

GPT-5 from OpenAI

1. Get your API key from OpenAI
2. Add GPT-5 to an agent on Continue Hub
3. Add OPENAI_API_KEY as a User Secret on Continue Hub here
4. Click Reload config in the agent selector in the Continue IDE extension

Kimi K2 from Moonshot AI

1. Get your API key from OpenRouter
2. Add Kimi K2 to an agent on Continue Hub
3. Add OPENROUTER_API_KEY as a User Secret on Continue Hub here
4. Click Reload config in the agent selector in the Continue IDE extension

Gemini 2.5 Pro from Google

1. Get your API key from Google AI Studio
2. Add Gemini 2.5 Pro to an agent on Continue Hub
3. Add GEMINI_API_KEY as a User Secret on Continue Hub here
4. Click Reload config in the agent selector in the Continue IDE extension

Grok 4 from xAI

1. Get your API key from xAI
2. Add Grok 4 to an agent on Continue Hub
3. Add XAI_API_KEY as a User Secret on Continue Hub here
4. Click Reload config in the agent selector in the Continue IDE extension

Devstral Medium from Mistral AI

1. Get your API key from Mistral AI
2. Add Devstral Medium to an agent on Continue Hub
3. Add MISTRAL_API_KEY as a User Secret on Continue Hub here
4. Click Reload config in the agent selector in the Continue IDE extension

gpt-oss-120b from OpenAI

1. Get your API key from OpenRouter
2. Add gpt-oss-120b to an agent on Continue Hub
3. Add OPENROUTER_API_KEY as a User Secret on Continue Hub here
4. Click Reload config in the agent selector in the Continue IDE extension

Local Models

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

1. Add Qwen3 Coder 30B to an agent on Continue Hub
2. Run the model with Ollama
3. Click Reload config in the agent selector in the Continue IDE extension

gpt-oss-20b

1. Add gpt-oss-20b to an agent on Continue Hub
2. Run the model with Ollama
3. Click Reload config in the agent selector in the Continue IDE extension

Devstral Small 27B

1. Add Devstral Small to an agent on Continue Hub
2. Run the model with Ollama
3. Click Reload config in the agent selector in the Continue IDE extension

Qwen2.5-Coder 7B from Qwen

1. Add Qwen2.5-Coder 7B to an agent on Continue Hub
2. Run the model with Ollama
3. Click Reload config in the agent selector in the Continue IDE extension

Gemma 3 4B from Google

1. Add Gemma 3 4B to an agent on Continue Hub
2. Run the model with Ollama
3. Click Reload config in the agent selector in the Continue IDE extension

Qwen2.5-Coder 1.5B from Qwen

1. Add Qwen2.5-Coder 1.5B to an agent on Continue Hub
2. Run the model with Ollama
3. Click Reload config in the agent selector in the Continue IDE extension