LiteLLM
LiteLLM, from BerriAI, is an open-source AI gateway that gives you a single OpenAI-compatible interface to 140+ providers and 2,500+ models, including OpenAI, Anthropic, Gemini, Bedrock, Azure, Mistral, Ollama and vLLM. You can use it as a lightweight Python SDK for direct calls, or deploy the proxy server as a centralized gateway for a team, with virtual keys, budgets, load balancing, rate limiting, request logging and LLM guardrails. It has become a default building block in the AI stack, with 45,000+ GitHub stars, 240M+ Docker pulls and over a billion requests served, and is used by companies including Netflix, Adobe and Stripe. The core is free; an enterprise tier adds JWT auth, SSO/SAML, audit logs, SLAs and dedicated support.
Work at LiteLLM? Manage this listing
Our take
LiteLLM is the open-source gateway that gives you one OpenAI-style interface to 140+ LLM providers and 2,500+ models, with cost tracking, load balancing, rate limits, logging and guardrails. Use it as a Python SDK or deploy the proxy as a team gateway. It's free and self-hosted, with an enterprise tier for SSO, audit logs and support; you run the ops.
Best for
Engineering teams that want a vendor-neutral, self-hosted gateway in front of every model, with budgets, keys and logging they control.
Pros
- Free and open-source, 140+ providers in OpenAI format
- Proxy adds virtual keys, budgets, load balancing and logging
- Battle-tested at scale (Netflix, Adobe, Stripe; 1B+ requests)
- Drops into existing code with minimal changes
Cons
- Self-hosting means you own deployment and uptime
- Advanced auth/SSO and support sit behind enterprise
- Proxy tuning and observability take setup
How it compares
Against hosted routers like OpenRouter, LiteLLM keeps the gateway in your own infrastructure; against Portkey, it's open-source-first and code-led rather than a managed control plane.
Full review
LiteLLM, from BerriAI, is an open-source AI gateway that gives you a single OpenAI-compatible interface to 140+ providers and 2,500+ models, including OpenAI, Anthropic, Gemini, Bedrock, Azure, Mistral, Ollama and vLLM. You can use it as a lightweight Python SDK for direct calls, or deploy the proxy server as a centralized gateway for a team, with virtual keys, budgets, load balancing, rate limiting, request logging and LLM guardrails. It has become a default building block in the AI stack, with 45,000+ GitHub stars, 240M+ Docker pulls and over a billion requests served, and is used by companies including Netflix, Adobe and Stripe. The core is free; an enterprise tier adds JWT auth, SSO/SAML, audit logs, SLAs and dedicated support.
Against hosted routers like OpenRouter, LiteLLM keeps the gateway in your own infrastructure; against Portkey, it's open-source-first and code-led rather than a managed control plane.
Cloudkart Trust Graph
4.4/5- Actual Utility5/5
Source: Initial LLM-authored rubric (backfill)
- Ease of Use4/5
Source: Initial LLM-authored rubric (backfill)
- Pricing Fairness5/5
Source: Initial LLM-authored rubric (backfill)
- Reliability4/5
Source: Initial LLM-authored rubric (backfill)
- Differentiation4/5
Source: Initial LLM-authored rubric (backfill)
Scored as of . Each score is versioned and auditable; vendors cannot buy it.
How this score is set
- Editorial rubric
- Primary signal — five dimensions, 4.4/5 average.
- Community reviews
- None yet.
- Pricing verified
- Not yet verified
- Independence
- Score set by our editorial team before any affiliate relationship is considered. No vendor can buy it.
Frequently asked questions
- Is LiteLLM free, and how much does it cost?
- LiteLLM is open source and free to self-host.
- Who is LiteLLM best for?
- Engineering teams that want a vendor-neutral, self-hosted gateway in front of every model, with budgets, keys and logging they control.
- How is LiteLLM rated on Cloudkart.ai?
- LiteLLM scores 4.4 out of 5 on the Cloudkart.ai rubric, which weighs actual utility, ease of use, pricing fairness, reliability and differentiation. Scores are set editorially and can never be bought.
Community reviews
No community reviews yet. Be the first to share how LiteLLM works for you.
Relevant tools
More tools in AI Coding Assistants.
Composio
Composio provides the execution infrastructure that connects AI agents to real software. It sits at the tooling and connectivity layer of the agent stack, giving developers one framework - SDKs, a CLI and 850+ pre-built connectors - to let agents act across apps such as GitHub, Slack and Salesforce. It handles the hard parts: complex authentication and OAuth, plus remote sandboxed environments for safe execution, exposed over the Model Context Protocol so agents can reason and then reliably take action. The platform is built for production, with SOC 2 and ISO 27001:2022 certifications and deployment across public cloud, VPC and on-premises. Composio operates from San Francisco and Bangalore and raised a $25M Series A led by Lightspeed, with angels including Vercel's Guillermo Rauch and HubSpot's Dharmesh Shah.
Claude Code
Terminal-based agentic coding tool from Anthropic for autonomous multi-step coding tasks.
GitHub Copilot
AI pair programmer integrated into VS Code, JetBrains IDEs, and GitHub - inline completions, chat, and autonomous agent mode.
Kiro
AWS agentic IDE built around spec-driven development: it writes a spec, then builds matching code, tests and docs across IDE, CLI and web.
Compare LiteLLM head-to-head: vs Composio · vs Claude Code · vs GitHub Copilot · vs Kiro