BerriAI/litellm vs songquanpeng/one-api

Compare BerriAI/litellm and songquanpeng/one-api using the current verified snapshot: positioning, license, deployment, use cases, limitations, and original sources.

BerriAI/litellm

LiteLLM is an open-source AI gateway and Python SDK that provides a single OpenAI-format interface to over 100 LLM providers. It centralizes routing, cost tracking, virtual keys, and guardrails, making it useful for enterprise teams and developers managing multiple external or self-hosted models.

License: License pending
Deployment: Python environment
Use cases: Enterprise teams, developers, and AI engineers who need to standardize API calls, manage costs, and apply consistent routing rules across multiple external LLM providers. · Teams requiring an admin dashboard and virtual keys to manage multi-tenant LLM usage.
Updated: 2026-07-17T06:30:35Z

Original project link

songquanpeng/one-api

One API consolidates API keys and distributes LLM requests across multiple model providers under a standard OpenAI-compatible API format. It targets developers and operations teams who need centralized key management and request routing for upstream LLM services.

License: MIT
Deployment: Docker / Docker Compose
Use cases: Chat Assistants
Updated: 2026-07-17T10:02:26Z

Original project link

How to choose

First eliminate options that fail required deployment, license, or use-case constraints; then inspect each detail page for limitations and direct evidence.