How do I get started with CacheGPT?
Sign up for a free account, generate your API key, and follow our Quick Start guide in the documentation.
What LLM providers are supported?
We support OpenAI (GPT-3.5, GPT-4), Anthropic (Claude), Google (Gemini), and custom endpoints.
How does the caching work?
We use semantic similarity matching with vector embeddings to identify and serve cached responses, reducing API costs by up to 80%.
Is my data secure?
Yes. We use TLS encryption for data in transit, AES-256 for data at rest, and follow industry best practices for security.
Can I delete my cached data?
Yes. You can delete cached data anytime through the CLI using "cachegpt clear" or via your dashboard.
What are the rate limits?
Free accounts have generous rate limits of 1000 requests per day. Contact us if you need higher limits.