LiteLLM
Unified interface for multiple LLM APIs
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for LiteLLM, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
LiteLLM is an open-source package that provides a standardized interface for calling multiple Large Language Model (LLM) APIs, including OpenAI, Azure, Anthropic, and many others. It simplifies the process of integrating different LLM providers by offering a consistent OpenAI-like input format, built-in streaming, logging, and load balancing capabilities.
Key features and capabilities
- UNIFIED API INTERFACE,
- MULTI-PROVIDER SUPPORT,
- BUILT-IN LOAD BALANCING,
- STREAMING RESPONSES,
- LOGGING AND ANALYTICS,
- EXTENSIBILITY,
- OPENAI-COMPATIBLE FORMAT
Use cases
- LLM API INTEGRATION,
- MULTI-MODEL DEPLOYMENT,
- AI APPLICATION DEVELOPMENT,
- COST OPTIMIZATION,
- PROVIDER FLEXIBILITY