πŸ€– AI Models Guide

AI Models for Clawdbot

Clawdbot supports multiple AI providers, from cloud-based models like Claude and GPT-4 to self-hosted options with Ollama.

Cloud AI Models

Cloud models offer the best quality and require no local hardware. You pay per usage via API.

ProviderModelBest ForSpeedPrice
AnthropicClaude 3.5 SonnetRecommendedBest overall, excellent at coding and reasoningFast$$
AnthropicClaude 3 OpusMost capable, complex tasksMedium$$$
AnthropicClaude 3 HaikuRecommendedFastest, budget-friendlyVery Fast$
OpenAIGPT-4 TurboStrong general purposeMedium$$$
OpenAIGPT-4oRecommendedMultimodal, fast responsesFast$$
OpenAIGPT-4o miniRecommendedVery affordable, good qualityVery Fast$
GoogleGemini 1.5 ProLong context, multimodalFast$$
GoogleGemini 1.5 FlashFast and affordableVery Fast$

Provider Details

🟠 Anthropic (Claude)
Our recommended provider

Claude models excel at nuanced conversations, coding, and following complex instructions.

  • βœ“Best overall quality
  • βœ“200K token context
  • βœ“Vision capabilities
Get API Key β†’
🟒 OpenAI (GPT-4)
Most popular choice

GPT-4 models are versatile and widely supported with excellent documentation.

  • βœ“Great ecosystem
  • βœ“DALL-E integration
  • βœ“Function calling
Get API Key β†’
πŸ”΅ Google (Gemini)
Google's latest models

Gemini offers excellent multimodal capabilities and very long context windows.

  • βœ“1M token context
  • βœ“Strong multimodal
  • βœ“Competitive pricing
Get API Key β†’

Local Models with Ollama

Run AI models locally for complete privacy and zero API costs. Requires decent hardware.

ModelSizeBest ForRequirements
Llama 3.1 70B40GBBest open-source performance32GB+ RAM, GPU recommended
Llama 3.1 8B4.7GBGreat balance of quality and speed16GB RAM
Mistral 7B4GBEfficient, good at reasoning16GB RAM
Mixtral 8x7B26GBMoE architecture, excellent quality32GB RAM, GPU recommended
Phi-32GBVery lightweight, surprisingly capable8GB RAM
CodeLlama 34B19GBSpecialized for coding32GB RAM, GPU
Setting Up Ollama
Run local models with Ollama

1. Install Ollama

curl -fsSL https://ollama.ai/install.sh | sh

2. Pull a Model

ollama pull llama3.1:8b

3. Configure Clawdbot

# In your .env file

OLLAMA_HOST=http://localhost:11434

DEFAULT_MODEL=llama3.1:8b

Choosing the Right Model

For Daily Conversations

Use Claude 3.5 Sonnet or GPT-4o for the best balance of quality and cost.

Recommended: Claude 3.5 Sonnet
For Budget Users

Claude Haiku or GPT-4o mini are 10x cheaper while still very capable.

Recommended: Claude 3 Haiku
For Coding Tasks

Claude 3.5 Sonnet excels at code generation and debugging.

Recommended: Claude 3.5 Sonnet
For Privacy

Run Llama or Mistral locally with Ollama. Your data never leaves your machine.

Recommended: Llama 3.1 8B

Ready to Get Started?

Install Clawdbot and connect to your preferred AI model.