Configure LiteLLM proxy server, virtual keys, and spend tracking.
npx skills add https://github.com/wenerme/ai --skill litellm-docs
Please help me install this Agent Skill. Skill: litellm-docs Source: https://github.com/wenerme/ai/tree/main/skills/litellm-docs Command: npx skills add https://github.com/wenerme/ai --skill litellm-docs
LiteLLM documentation helps you configure and troubleshoot a unified, OpenAI-compatible interface for 100+ LLM providers, including proxy routing, fallbacks, caching, observability, secrets, and guardrails.
Ask about how to configure LiteLLM Proxy for multi-provider routing with spend tracking and caching for a chat completion workload.
High-intent search queries and answers about installing and using this skill.
To set up the LiteLLM proxy server, deploy the proxy to enable load balancing, virtual keys, spend tracking, rate limiting, and model routing across 100+ LLM providers. The proxy exposes a unified OpenAI-compatible API for chat completions.
The best way to track token spend and set budgets with LiteLLM is by configuring virtual keys through the proxy server. This enables precise spend tracking and budget enforcement across multiple providers and routing configurations.
Yes, LiteLLM supports caching using Redis, S3, and in-memory storage. Configuring caching through the proxy server reduces latency and costs for repeated chat completion workloads across your configured LLM providers.
To configure fallback routing behavior in LiteLLM, use the proxy server settings to define fallback models. This ensures requests automatically reroute to backup providers if the primary LLM provider fails or returns errors.
Yes, you can integrate LiteLLM with secret managers for secure credential handling and observability tools like Datadog, Langfuse, Prometheus, and OTEL. This integration provides comprehensive production monitoring and secure provider configuration.
You use an OpenAI-compatible Python SDK to normalize API calls across 100+ LLM providers. This approach simplifies provider configuration, routing, and fallback strategies by maintaining a consistent interface for all vendor interactions.
kettleofketchupDeploy an OpenAI-compatible API gateway routing requests to 100+ LLM providers.
frankxaiImplement structured logging, metrics, tracing, and alerting for production applications.
martinrojasIntegrate Portkey AI Gateway into TypeScript and JavaScript applications for LLM routing.
tylerjrbuellConfigure per-provider behavior and adapter hooks for LLM interactions.
