• 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

​
Best Models by Role

​
Learn More About Models

Finish 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 Sonnet 4.6 from Anthropic
  1. Get your API key from Anthropic
  2. Add Claude Sonnet 4.6 to your Finish config
  3. Add ANTHROPIC_API_KEY to your environment or config
  4. Click Reload config in the config selector in the Finish IDE extension
Qwen Coder 3 480B from Qwen
  1. Get your API key from OpenRouter
  2. Add Qwen Coder 3 480B your Finish config
  3. Add OPENROUTER_API_KEY to your environment or config
  4. Click Reload config in the config selector in the Finish IDE extension
GPT-5 from OpenAI
  1. Get your API key from OpenAI
  2. Add GPT-5 your Finish config
  3. Add OPENAI_API_KEY to your environment or config
  4. Click Reload config in the config selector in the Finish IDE extension
Kimi K2 from Moonshot AI
  1. Get your API key from OpenRouter
  2. Add Kimi K2 your Finish config
  3. Add OPENROUTER_API_KEY to your environment or config
  4. Click Reload config in the config selector in the Finish IDE extension
Gemini 3.1 Pro from Google
  1. Get your API key from Google AI Studio
  2. Add Gemini 3.1 Pro your Finish config
  3. Add GEMINI_API_KEY to your environment or config
  4. Click Reload config in the config selector in the Finish IDE extension
Grok Code Fast 1 from xAI
  1. Get your API key from xAI
  2. Add Grok Code Fast 1 your Finish config
  3. Add XAI_API_KEY to your environment or config
  4. Click Reload config in the config selector in the Finish IDE extension
Devstral Medium from Mistral AI
  1. Get your API key from Mistral AI
  2. Add Devstral Medium your Finish config
  3. Add MISTRAL_API_KEY to your environment or config
  4. Click Reload config in the config selector in the Finish IDE extension
gpt-oss-120b from OpenAI
  1. Get your API key from OpenRouter
  2. Add gpt-oss-120b your Finish config
  3. Add OPENROUTER_API_KEY to your environment or config
  4. Click Reload config in the config selector in the Finish IDE extension

​
Local Models

Need a quick setup walkthrough? Check out Using Ollama with Finish: A Developer’s Guide.
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 your Finish config
  2. Run the model with Ollama
  3. Click Reload config in the config selector in the Finish IDE extension
gpt-oss-20b
  1. Add gpt-oss-20b your Finish config
  2. Run the model with Ollama
  3. Click Reload config in the config selector in the Finish IDE extension
Devstral Small 27B
  1. Add Devstral Small your Finish config
  2. Run the model with Ollama
  3. Click Reload config in the config selector in the Finish IDE extension
Qwen2.5-Coder 7B from Qwen
  1. Add Qwen2.5-Coder 7B your Finish config
  2. Run the model with Ollama
  3. Click Reload config in the config selector in the Finish IDE extension
Gemma 3 4B from Google
  1. Add Gemma 3 4B your Finish config
  2. Run the model with Ollama
  3. Click Reload config in the config selector in the Finish IDE extension
Qwen2.5-Coder 1.5B from Qwen
  1. Add Qwen2.5-Coder 1.5B your Finish config
  2. Run the model with Ollama
  3. Click Reload config in the config selector in the Finish IDE extension