platoseedplatoseed
Call every LLM API like it's OpenAI [100+ LLMs]
LiteLLM is an open-source LLM Gateway with 18K+ stars on GitHub and trusted by companies like Rocket Money, Samsara, Lemonade, and Adobe. LiteLLM provides an open source Python SDK and Python FastAPI Server that allows calling 100+ LLM APIs (Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic) in the OpenAI format We have raised a $1.6M seed round from Y Combinator, Gravity Fund and Pioneer Fund
LiteLLM provides an AI gateway that manages authentication, load balancing, and spend tracking across 100+ LLMs, all in the OpenAI-compatible format. It targets platform teams needing broad LLM access and unified billing across providers. It offers both cloud and on-prem options with enterprise features.
LiteLLM acts as an AI gateway/proxy that centralizes model access, fallbacks, and spend tracking across 100+ LLM providers (OpenAI, Azure, Bedrock, GCP, HF models, etc.). It includes OpenAI-compatible interfaces, rate limiting, budgets, prompts management, logging to S3/GCS, and support for both cloud and on-prem deployments. The product surfaces as a gateway + Python SDK + dashboards for budgets, usage, and observability, with enterprise features like JWT auth, SSO, audit logs, and custom SLAs.
Who it’s for: Platform teams and GenAI teams at large organizations that need centralized LLM access for developers, with spend tracking and multi-provider model access.
Hiring/roadmap discussions mentioned; enterprise features and on-prem deployment imply growth and traction with large customers
Add 100+ new LLMs to your application, with a drop-in replacement for the openai chat completion call.
LiteLLM provides a single interface to call multiple LLM APIs (Azure, Anthropic, Replicate, etc.) using the OpenAI completion format. It standardizes inputs/outputs, handles errors, and offers observability, enabling added LLM providers—100+ new integrations—via a single environment variable without code changes.
From the original launch (Aug 2023) — may be outdated.
Formerly “Clerkie”, “BerriAI” · why startups rename →
Streamlining LLM application management for enterprises
LLM Observability for Developers
