AI Models
OpenClaw supports multiple AI providers. Choose the one that fits your needs and budget.
Every AI model has different strengths — some are fast and cheap, others are more capable but cost more per request. OpenClaw lets you swap providers with a single configuration change, so you are never locked in. Below we compare pricing, context windows, and real-world performance so you can make an informed choice. If you want zero API costs, scroll down to the Ollama section for fully local, offline models.
Start here if you just want the answer
These three choices cover the most common decisions: best quality, lowest recurring cost, and full local privacy.
Best quality
Anthropic
The most capable model for complex tasks. Excellent at coding, analysis, and nuanced conversations.
Input
$3.00/1M
Output
$15.00/1M
Context
200K tokens
Best at
Best overall quality
Tradeoff
Higher cost
Lowest cost
OpenAI
Budget-friendly option from OpenAI. Decent performance at a fraction of the cost.
Input
$0.15/1M
Output
$0.60/1M
Context
128K tokens
Best at
Very affordable
Tradeoff
Limited capabilities
Private + local
Ollama (Local)
Run AI completely locally with no API costs. Requires decent hardware but offers full privacy.
Input
Free
Output
Forever
Context
8K-128K tokens
Best at
100% free
Tradeoff
Requires good hardware
Quick comparison
Scan the tradeoffs first. Open the setup guide only after you know which model fits your workload.
| Model | Provider | Input | Output | Context | Best at | Tradeoff | |
|---|---|---|---|---|---|---|---|
Claude 3.5 Sonnet RecommendedThe most capable model for complex tasks. Excellent at coding, analysis, and nuanced conversations. | Anthropic | $3.00/1M | $15.00/1M | 200K tokens | Best overall quality | Higher cost | Open setup guide → |
Claude 3.5 Haiku Fast and affordable option for simpler tasks. Great for quick responses and high-volume usage. | Anthropic | $0.25/1M | $1.25/1M | 200K tokens | Very fast | Less capable on complex tasks | Open setup guide → |
GPT-4o OpenAI's flagship multimodal model. Good all-around performance with image understanding. | OpenAI | $2.50/1M | $10.00/1M | 128K tokens | Multimodal (images) | Smaller context than Claude | Open setup guide → |
GPT-4o mini Budget-friendly option from OpenAI. Decent performance at a fraction of the cost. | OpenAI | $0.15/1M | $0.60/1M | 128K tokens | Very affordable | Limited capabilities | Open setup guide → |
Gemini 1.5 Flash Google's fast model with massive context window. Free tier available for low usage. | Free tier | Then $0.075/1M | 1M tokens | Huge context window | Quality varies | Open setup guide → | |
Llama 3.1 / Mistral Run AI completely locally with no API costs. Requires decent hardware but offers full privacy. | Ollama (Local) | Free | Forever | 8K-128K tokens | 100% free | Requires good hardware | Open setup guide → |
Detailed profiles
Use the deeper cards below when you are deciding between two close options.
Anthropic
The most capable model for complex tasks. Excellent at coding, analysis, and nuanced conversations.
Input
$3.00/1M
Output
$15.00/1M
Context
200K tokens
Pros
- Best overall quality
- Excellent coding ability
- Strong reasoning
- Good at following instructions
Cons
- Higher cost
- Slower than smaller models
Anthropic
Fast and affordable option for simpler tasks. Great for quick responses and high-volume usage.
Input
$0.25/1M
Output
$1.25/1M
Context
200K tokens
Pros
- Very fast
- Low cost
- Good quality for price
- Same context window
Cons
- Less capable on complex tasks
- May miss nuances
OpenAI
OpenAI's flagship multimodal model. Good all-around performance with image understanding.
Input
$2.50/1M
Output
$10.00/1M
Context
128K tokens
Pros
- Multimodal (images)
- Fast
- Good all-around
- Large ecosystem
Cons
- Smaller context than Claude
- Variable quality
OpenAI
Budget-friendly option from OpenAI. Decent performance at a fraction of the cost.
Input
$0.15/1M
Output
$0.60/1M
Context
128K tokens
Pros
- Very affordable
- Decent quality
- Fast
Cons
- Limited capabilities
- May struggle with complex tasks
Google's fast model with massive context window. Free tier available for low usage.
Input
Free tier
Output
Then $0.075/1M
Context
1M tokens
Pros
- Huge context window
- Free tier
- Fast
- Multimodal
Cons
- Quality varies
- Less tested with OpenClaw
Ollama (Local)
Run AI completely locally with no API costs. Requires decent hardware but offers full privacy.
Input
Free
Output
Forever
Context
8K-128K tokens
Pros
- 100% free
- Complete privacy
- No internet needed
- No rate limits
Cons
- Requires good hardware
- Lower quality than cloud models
- Setup complexity
Our Recommendation
For most users, we recommend starting with Claude 3.5 Sonnet for the best quality, or Ollama with Llama 3.1 if you want to run completely free and private.
You can switch models anytime in your OpenClaw configuration. Many users configure multiple models and switch based on the task.