Model setup

info

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

YAML

Package or config.yaml

models:
  - name: Claude 3.5 Sonnet
    provider: anthropic
    model: claude-3-5-sonnet-latest
    apiKey: <YOUR_ANTHROPIC_API_KEY>

JSON

config.json

{
  "models": [
    {
      "title": "Claude 3.5 Sonnet",
      "provider": "anthropic",
      "model": "claude-3-5-sonnet-latest",
      "apiKey": "<YOUR_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).

YAML

Together

Package or config.yaml

models:
  - name: "Llama 3.1 405B"
    provider: "together"
    model: "llama3.1-405b"
    apiKey: <YOUR_TOGETHER_API_KEY>

Groq

Package or config.yaml

models:
  - name: "Llama 3.1 405B"
    provider: "groq"
    model: "llama3.1-405b"
    apiKey: <YOUR_GROQ_API_KEY>

vLLM

Package or config.yaml

models:
  - name: "Llama 3.1 405B"
    provider: "vllm"
    model: "llama3.1-405b"

Ollama

Package or config.yaml

models:
  - name: "Llama 3.1 405B"
    provider: "ollama"
    model: "llama3.1:405b"

JSON

Together

config.json

{
  "models": [
    {
      "title": "Llama 3.1 405B",
      "provider": "together",
      "model": "llama3.1-405b",
      "apiKey": "<YOUR_TOGETHER_API_KEY>"
    }
  ]
}

Groq

config.json

{
  "models": [
    {
      "title": "Llama 3.1 405B",
      "provider": "groq",
      "model": "llama3.1-405b",
      "apiKey": "<YOUR_GROQ_API_KEY>"
    }
  ]
}

vLLM

config.json

{
  "models": [
    {
      "title": "Llama 3.1 405B",
      "provider": "vllm",
      "model": "llama3.1-405b"
    }
  ]
}

Ollama

config.json

{
  "models": [
    {
      "title": "Llama 3.1 405B",
      "provider": "ollama",
      "model": "llama3.1:405b"
    }
  ]
}

GPT-4o from OpenAI

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

YAML

Package or config.yaml

models:
  - name: GPT-4o
    provider: openai
    model: ''
    apiKey: <YOUR_OPENAI_API_KEY>

JSON

config.json

{
  "models": [
    {
      "title": "GPT-4o",
      "provider": "openai",
      "model": "",
      "apiKey": "<YOUR_OPENAI_API_KEY>"
    }
  ]
}

Grok-2 from xAI

If you prefer to use a model from xAI, then we recommend Grok-2.

YAML

Package or config.yaml

models:
  - name: Grok-2
    provider: xAI
    model: grok-2-latest
    apiKey: <YOUR_XAI_API_KEY>

JSON

config.json

{
  "models": [
    {
      "title": "Grok-2",
      "provider": "xAI",
      "model": "grok-2-latest",
      "apiKey": "<YOUR_XAI_API_KEY>"
    }
  ]
}

Gemini 1.5 Pro from Google

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

YAML

Package or config.yaml

models:
  - name: Gemini 1.5 Pro
    provider: gemini
    model: gemini-1.5-pro-latest
    apiKey: <YOUR_GEMINI_API_KEY>

JSON

config.json

{
  "models": [
    {
      "title": "Gemini 1.5 Pro",
      "provider": "gemini",
      "model": "gemini-1.5-pro-latest",
      "apiKey": "<YOUR_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).

YAML

Ollama

Package or config.yaml

models:
  - name: Llama 3.1 8B
    provider: ollama
    model: llama3.1:8b

LM Studio

Package or config.yaml

models:
  - name: Llama 3.1 8B
    provider: lmstudio
    model: llama3.1:8b

JSON

Ollama

config.json

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

LM Studio

config.json

{
  "models": [
    {
      "title": "Llama 3.1 8B",
      "provider": "lmstudio",
      "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).

YAML

Ollama

Package or config.yaml

models:
  - name: DeepSeek Coder 2 16B
    provider: ollama
    model: deepseek-coder-v2:16b

LM Studio

Package or config.yaml

models:
  - name: DeepSeek Coder 2 16B
    provider: lmstudio
    model: deepseek-coder-v2:16b

JSON

Ollama

config.json

{
  "models": [
    {
      "title": "DeepSeek Coder 2 16B",
      "provider": "ollama",
      "model": "deepseek-coder-v2:16b",
      "apiBase": "http://localhost:11434"
    }
  ]
}

LM Studio

config.json

{
  "models": [
    {
      "title": "DeepSeek Coder 2 16B",
      "provider": "lmstudio",
      "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