Choose Your AI
ClawHost offers 5 AI models from three world-class providers. Choose your provider and model at deployment. Here's how they compare.
AVAILABLE PROVIDERS
Two models: Opus 4.6 for deep reasoning, creative writing, and detailed analysis — the thinking model. Sonnet 4.5 for an optimal balance of capability and cost, great for everyday conversations and tasks.
From $9.00 / 1M tokens
From $45.00 / 1M tokens
OpenAI's latest flagship. Strong at following complex instructions, code generation, structured output, and general-purpose tasks. The all-rounder.
$5.25 / 1M tokens
$42.00 / 1M tokens
Two models: Gemini 2.5 Pro for cost-effective, high-volume use cases where speed matters. Gemini 3 Pro for enhanced reasoning and Google's latest capabilities with a 2M token context window.
From $3.75 / 1M tokens
From $30.00 / 1M tokens
CHOOSE YOUR MODEL
Pick your provider and model at deploy time. Each provider offers one or more models with different capabilities and pricing. You can change your model later from the dashboard.
HOW AI REQUESTS WORK
Your bot never calls AI providers directly. All requests go through our secure proxy, which handles authentication, token counting, credit deduction, and content moderation.
1. Bot sends message to ClawHost proxy
2. Proxy validates gateway token
3. Content moderation checks message
4. Proxy forwards to AI provider
5. Response streamed back to bot
6. Token usage logged and credits deducted
PROVIDER COMPARISON
| Feature | Anthropic | OpenAI | |
|---|---|---|---|
| Best for | Deep reasoning | General tasks | Speed & volume |
| Cost per message | Higher | Medium | Lower |
| Response speed | Moderate | Fast | Fastest |
| Creative writing | Excellent | Very good | Good |
| Code generation | Excellent | Excellent | Very good |
| Multilingual | 50+ languages | 50+ languages | 50+ languages |