Output that fits your existing stack.
These are integration patterns for passing LLMSlim output into model clients. They are not provider-specific adapters, and provider calls remain your application’s responsibility.
LLM Provider3 examples
Python integration
OpenAI
Compress Python application context before an OpenAI SDK request.
Read guidePython integration
Anthropic
Prepare long Python-managed context before an Anthropic SDK request.
Read guidePython integration
Google Gemini
Compress retrieved Python context before a Gemini SDK request.
Read guide