Skip to main content

Model setup

info

This page recommends models and providers for Chat. Read more about how to set up your config.json here.

Best overall experience​

For the best overall Chat experience, you will want to use a 400B+ parameter model or one of the frontier models.

Claude Sonnet 3.5 from Anthropic​

Our current top recommendation is Claude Sonnet 3.5 from Anthropic.

config.json
 "models": [
   {
     "title": "Claude 3.5 Sonnet",
     "provider": "anthropic",
     "model": "claude-3-5-sonnet-20240620",
     "apiKey": "[ANTHROPIC_API_KEY]"
   }
 ]

Llama 3.1 405B from Meta​

If you prefer to use an open-weight model, then Llama 3.1 405B from Meta is your best option right now. You will need to decide if you use it through a SaaS model provider (e.g. Together or Groq) or self-host it (e.g. using vLLM or Ollama).

config.json
    "models": [
        {
            "title": "Llama 3.1 405B",
            "provider": "together",
            "model": "llama3.1-405b",
            "apiKey": "[TOGETHER_API_KEY]"
        }
    ]

GPT-4o from OpenAI​

If you prefer to use a model from OpenAI, then we recommend GPT-4o.

config.json
 "models": [
   {
     "title": "GPT-4o",
     "provider": "openai",
     "model": "",
     "apiKey": "[OPENAI_API_KEY]"
   }
 ]

Gemini 1.5 Pro from Google​

If you prefer to use a model from Google, then we recommend Gemini 1.5 Pro.

config.json
  "models": [
    {
      "title": "Gemini 1.5 Pro",
      "provider": "gemini",
      "model": "gemini-1.5-pro-latest",
      "apiKey": "[GEMINI_API_KEY]"
    }
  ]

Local, offline experience​

For the best local, offline Chat experience, you will want to use a model that is large but fast enough on your machine.

Llama 3.1 8B​

If your local machine can run an 8B parameter model, then we recommend running Llama 3.1 8B on your machine (e.g. using Ollama or LM Studio).

config.json
    "models": [
        {
            "title": "Llama 3.1 8B",
            "provider": "ollama",
            "model": "llama3.1-8b"
        }
    ]

DeepSeek Coder 2 16B​

If your local machine can run a 16B parameter model, then we recommend running DeepSeek Coder 2 16B (e.g. using Ollama or LM Studio).

config.json
    "models": [
        {
            "title": "DeepSeek Coder 2 16B",
            "provider": "ollama",
            "model": "deepseek-coder-v2:16b"
        }
    ]

Other experiences​

There are many more models and providers you can use with Chat beyond those mentioned above. Read more here