# LiteLLM > Source: https://agentsindex.ai/litellm Gives one organization governed, budgeted access to 140+ model providers with spend tracking and routing. - Best for: Platform teams who need one gateway for multi-model access, spend control, and fallbacks. Starting price Free Open Source plan From [litellm.ai/pricing](https://www.litellm.ai/pricing), checked 28 October 2026 - MCP server Yes - API Yes - Open source Partly - Self-host Yes - GitHub stars: 61.3k [Docs](https://docs.litellm.ai/docs/) [GitHub](https://github.com/BerriAI/litellm) What we checked - Pages last read: 14 November 2026 - Facts checked: 5 facts From 6 sources, read 28 October 2026 - AI answers: Not named in any of 62 Buyer questions, November 2026 [How we check](https://agentsindex.ai/methodology) [Editorial policy](https://agentsindex.ai/editorial-policy#not-for-sale) [Visit LiteLLM](https://agentsindex.ai/go/litellm) [Compare](https://agentsindex.ai/compare?cat=agent-tools-and-integrations&products=litellm) ## At a glance - Category: [Agent tools and integrations](https://agentsindex.ai/categories/agent-tools-and-integrations) - Tags: Freemium, Open source, Self-hosted ### Code - Last push: 15 October 2026 ### For developers - Works with: OpenAI, Azure, Bedrock, Google Cloud, s3, gcs and 10 more ## What is LiteLLM? LiteLLM is an OpenAI-compatible gateway for platform teams that routes LLM requests across many providers without rewriting app integrations. It includes Model Access, LLM Fallbacks, Spend Tracking, Budgets & Rate Limits, Virtual Keys, and LLM Observability. It integrates with Langfuse, Arize Phoenix, Langsmith, OTEL, Datadog, and OpenTelemetry, and is used by Netflix and Lemonade. Plans run Open Source $0 and Enterprise custom. ## What it actually does well LiteLLM's core pitch holds up: one Docker container gives you a virtual-key gateway in front of 100+ LLM providers (OpenAI, Anthropic, Bedrock, Vertex, Azure, and long-tail providers like Cerebras or Nebius) behind a single OpenAI-compatible `/chat/completions` endpoint, with budgets, rate limits, fallbacks, and Prometheus metrics included in the free tier — not gated behind a paywall ([litellm.ai/pricing](https://www.litellm.ai/pricing)). It also ships as a plain Python SDK (`pip install litellm`) for teams that just want provider-agnostic calls without running a proxy at all. The provider table is the widest of any gateway we've checked — 100+ providers each documented individually, including narrower ones like OCI, Heroku, and Databricks ([pypi.org/pypi/litellm/json](https://pypi.org/pypi/litellm/json)). ## Pricing: free core, custom-quoted Enterprise Open Source is $0, self-hosted, no license fee, and the vendor states this explicitly rather than gating features behind a trial clock ([litellm.ai/pricing](https://www.litellm.ai/pricing)). Enterprise — SSO/SCIM, audit logs, multi-region control plane, secret-manager integrations, 24/7 support SLAs — has no published price; it's quoted against your annual gateway request capacity and deployment shape, with procurement via AWS/Azure Marketplace and a 30-day trial license available on request ([docs.litellm.ai/docs/enterprise](https://docs.litellm.ai/docs/enterprise)). SSO itself is free for up to 5 users before a license is required ([docs.litellm.ai/docs/enterprise](https://docs.litellm.ai/docs/enterprise)). One thing worth knowing before you self-host: the `pip install litellm[proxy]` extra pulls in `litellm-enterprise`, a separate package under a proprietary license (PyPI reports `LicenseRef-Proprietary`), whose enterprise features simply stay inert until you add a `LITELLM_LICENSE` key ([pypi.org/pypi/litellm-enterprise/json](https://pypi.org/pypi/litellm-enterprise/json), [docs.litellm.ai/docs/enterprise](https://docs.litellm.ai/docs/enterprise)). The repo's root `LICENSE` file is accurate but easy to misread at a glance — MIT covers everything outside the `enterprise/` directory, and that directory carries its own commercial license restricting redistribution and modification without a paid seat count ([raw.githubusercontent.com/BerriAI/litellm/main/LICENSE](https://raw.githubusercontent.com/BerriAI/litellm/main/LICENSE), [raw.githubusercontent.com/BerriAI/litellm/main/enterprise/LICENSE.md](https://raw.githubusercontent.com/BerriAI/litellm/main/enterprise/LICENSE.md)). ## Repository activity and scale Actively pushed to and not archived ([github.com/BerriAI/litellm](https://github.com/BerriAI/litellm)). PR velocity is high: a spot check of merged PRs in the last day alone shows automated provider price-sync bots, new-model cost-map additions, and active Rust-crate feature work landing within hours of being opened ([api.github.com/search/issues](https://api.github.com/search/issues?q=repo:BerriAI/litellm+is:pr+is:merged+merged:%3E2026-09-01)). 5,247 open issues is a large backlog for a project this size, which is worth knowing if you're expecting fast turnaround on a niche bug rather than a priced support channel. ## The Rust rewrite: real, but still narrow LiteLLM announced in June 2026 that it's rewriting the gateway's hot path in Rust, claiming 15x throughput (453 to 6,782 req/s), 11x lower memory (359MB to 32MB), and per-request overhead dropping from ~7.5ms to ~0.05ms in the vendor's own harness ([docs.litellm.ai/blog/litellm-rust-launch](https://docs.litellm.ai/blog/litellm-rust-launch)). As of the current beta docs, this is opt-in per model (`rust: true` in `litellm_params`) and covers a specific subset: non-streaming `/chat/completions` on Anthropic and Bedrock (Converse) only, the Anthropic `/v1/messages` route on Anthropic and Azure AI, Bedrock audio transcription, and OpenAI Responses-API websockets — anything with tool calls, images, `response_format`, streaming (except `/v1/messages`), or extended thinking silently falls back to the existing Python path ([docs.litellm.ai/docs/proxy/rust_gateway](https://docs.litellm.ai/docs/proxy/rust_gateway)). The standalone all-Rust server (Mode 2, the one that would actually deliver the throughput numbers end-to-end) has no published Docker image yet — you'd build it yourself from source. Treat the benchmark numbers as a ceiling for a narrow, still-growing code path, not as today's typical request latency. ## Security disclosures Four CVEs are publicly disclosed against the LiteLLM proxy: an authenticated SSRF/credential-exfiltration bug (CVE-2026-84377, medium, CVSS 6.5, patched in 1.96.2 with backports to 1.88.x), a second SSRF via a `user_config` parameter that bypassed the existing guard (CVE-2026-59823, medium, patched 1.83.9), a path-traversal arbitrary file write via Skills archive uploads (CVE-2026-59820, medium, patched 1.83.7), and a local file read via OIDC file references requiring admin access (CVE-2026-59819, low, patched 1.83.10) ([api.github.com/repos/BerriAI/litellm/security-advisories](https://api.github.com/repos/BerriAI/litellm/security-advisories)). All were fixed within the same or an adjacent minor line; none affects a hosted service since LiteLLM only ships self-hosted. The vendor holds a SOC 2 Type II report available through its Trust Center ([trust.litellm.ai/controls](https://trust.litellm.ai/controls)) and states it runs no telemetry and stores no data on its own servers for self-hosted deployments ([docs.litellm.ai/docs/data_security](https://docs.litellm.ai/docs/data_security)); there's no public bug-bounty program. ## Upgrade cadence to plan around LiteLLM ships a new minor version roughly weekly and, as policy effective 29 June 2026, only patches the four most recent stable minor lines — anything older stops receiving fixes entirely, with no long-term-support track ([docs.litellm.ai/docs/enterprise](https://docs.litellm.ai/docs/enterprise)). For a self-hosted gateway holding provider credentials, that's a real operational commitment: falling more than a few minor versions behind means the next CVE patch may not backport to your version. ## Company and funding LiteLLM is built by BerriAI, a Y Combinator W23 company founded by Krrish Dholakia and Ishaan Jaffer ([ycombinator.com/companies/litellm](https://www.ycombinator.com/companies/litellm)). Crunchbase lists the team at 1–10 employees ([crunchbase.com/organization/litellm](https://www.crunchbase.com/organization/litellm)). Reported funding is a $1.6M seed round from Y Combinator, Gravity Fund, and Pioneer Fund, alongside a reported $7M ARR figure — both figures come from a single August 2026 Dealroom news item and have not been corroborated against a company filing or press release; treat the ARR number as unverified ([app.dealroom.co/news/feed/litellm-raises-1-6m-seed-funding-amid-security-challenges-hits-7m-arr](http://app.dealroom.co/news/feed/litellm-raises-1-6m-seed-funding-amid-security-challenges-hits-7m-arr), read from a search result). The vendor's own README and YC page name Netflix, Stripe, Adobe, and NASA among adopters; these are vendor-supplied logos, not independently confirmed customer relationships. Our take Check whether the Open Source tier covers the governance features you need, since Enterprise adds JWT auth, SSO, and audit logs. If those controls are required for your rollout, the free tier alone will not be enough. ## How much does LiteLLM cost? Prices excluding tax, as LiteLLM publishes them. - Open Source · Free - Free forever, self-hosted - No credit card - Enterprise · Get In Touch - 30-day trial key to evaluate Enterprise [![LiteLLM](https://agentsindex.ai/img/1024/screenshots/litellm/pricing.webp)](https://agentsindex.ai/img/1920/screenshots/litellm/pricing.webp) Pricing page, captured 19 October 2026 [litellm.ai/pricing](https://www.litellm.ai/pricing), checked 28 October 2026 ### All plans and limits | Plan | Price | Main limits | | --- | --- | --- | | Open Source | $0 a month | None stated | | Enterprise | Price on request | None stated | Read 14 November 2026 from [litellm.ai/pricing](https://www.litellm.ai/pricing). ## For AI agents - MCP server: Yes - API: Yes [Developer docs](https://docs.litellm.ai/docs/) ## What we checked on LiteLLM Yes Partly No What it costs to start Yes ### What the price counts Two paths: the self-hosted open-source gateway carries no license fee, and the paid Enterprise license is quoted only, sized to annual gateway request capacity, deployment architecture and support, explicitly not per token. > Enterprise pricing is sized to your annual gateway request capacity, deployment architecture, and support needs — never per token. Plans section, note under the Open Source and Enterprise plan cards [litellm.ai/pricing](https://www.litellm.ai/pricing) Checked 28 October 2026 What it costs to start Yes ### Free to use The open-source gateway is a standing free tier, self-hosted with no license fee, covering virtual keys, budgets, spend tracking, fallbacks and Prometheus metrics; a separate 30-day Enterprise trial key exists on top. > Is the open-source version really free for production? Yes. Self-host LiteLLM OSS with no license fee, forever. Pricing FAQ, question 01 [litellm.ai/pricing](https://www.litellm.ai/pricing) Checked 28 October 2026 How you build with it Yes ### Public API The proxy exposes OpenAI-format endpoints such as /v1/chat/completions, /v1/responses and /v1/messages, plus a published OpenAPI management API for models, credentials, keys, teams and users. > requests land on the proxy's /v1/messages (Anthropic) or /v1/chat/completions and /v1/responses (OpenAI) endpoints Run coding agents through the proxy section, paragraph on pinning the model [docs.litellm.ai/docs/proxy/management_c…](https://docs.litellm.ai/docs/proxy/management_cli) Checked 28 October 2026 How you build with it Yes ### MCP server The gateway acts as an MCP gateway: it fronts MCP servers over streamable HTTP, SSE and stdio, lists and calls their tools, and scopes access by key, team or organization. stdio needs a flag set at startup. > LiteLLM Proxy provides an MCP Gateway that allows you to use a fixed endpoint for all MCP tools and control MCP access by Key, Team. MCP Overview, opening paragraph and Overview table [docs.litellm.ai/docs/mcp](https://docs.litellm.ai/docs/mcp) Checked 28 October 2026 How you build with it Partly ### Open source Most of the repository is MIT licensed, but code under the enterprise/ directory carries a separate license, and Enterprise features in the same image are gated behind a paid license key. > All content that resides under the "enterprise/" directory of this repository, if that directory exists, is licensed under the license defined in… LICENSE file, portions clause above the MIT text [raw.githubusercontent.com/BerriAI/litel…](https://raw.githubusercontent.com/BerriAI/litellm/main/LICENSE) Checked 28 October 2026 ## Questions about LiteLLM - How much does LiteLLM cost?: LiteLLM's Open Source plan is free. It also sells a paid Enterprise plan. From litellm.ai/pricing, checked 28 October 2026. - Does LiteLLM have an API or an MCP server?: It has an API. It has an MCP server. - Is LiteLLM open source, and can you host it yourself?: Part of it is open source. You can host it yourself. - What have we checked on LiteLLM?: 5 facts, under these headings: What it costs to start, how you build with it. - How do we check LiteLLM?: We hold 5 facts on LiteLLM, quoted from 6 pages. Facts and price last checked 28 October 2026. Last change found 21 March 2026. [How we check every listing](https://agentsindex.ai/methodology) ## Sources and changes Last changed 21 March 2026 Sources 6 - Read 14 November 2026 · [litellm.ai](https://www.litellm.ai/pricing) /pricing - Read 14 November 2026 · [docs.litellm.ai](https://docs.litellm.ai/) / - Read 12 November 2026 · [litellm.ai](https://litellm.ai/) / - Read 28 October 2026 · [raw.githubusercontent.com](https://raw.githubusercontent.com/BerriAI/litellm/main/LICENSE) /BerriAI/litellm/main/LICENSE - Read 28 October 2026 · [docs.litellm.ai](https://docs.litellm.ai/docs/mcp) /docs/mcp - Read 28 October 2026 · [docs.litellm.ai](https://docs.litellm.ai/docs/proxy/management_cli) /docs/proxy/management_cli Repository - Stars: 61,332 - Last push: 15 October 2026 ## Similar in Agent tools and integrations [See all in Agent tools and integrations](https://agentsindex.ai/categories/agent-tools-and-integrations) - [ERIUS PHONE](https://agentsindex.ai/eriusphone) Isolated cloud Android phones rented by the month that keep an agent's apps and sign-ins between sessions. From about $44 a month - [TinyFish](https://agentsindex.ai/tinyfish) Web search, page fetching, cloud browsers and a web automation agent for AI agents, with search and fetch free. Free plan, then $0.002 per minute - [Smithery](https://agentsindex.ai/smithery) Public MCP server registry, now run by Arcade, listing direct vendor MCP URLs after its proxy shut down. Free plan - [UI Discovery](https://agentsindex.ai/uidiscovery) A library of real websites, iOS apps and dashboards with each one's palette, fonts and original build prompt. From $20 a month ## From our research [All research](https://agentsindex.ai/blog) - [Comparison](https://agentsindex.ai/blog/workflow-automation-where-each-platform-stops-being-free) 15 Aug 2026 Workflow automation for AI agents: where free tiers end Zapier, Make, n8n, Activepieces, Pipedream and Trigger.dev meter in six different units. Which free tier survives real agent work, which runs out first. - [Data table](https://agentsindex.ai/data/ai-assistant-apps-security) 12 Nov 2026 AI assistants for work: SOC 2, ISO 27001, GDPR and SSO - [Data table](https://agentsindex.ai/data/customer-service-agents-security) 14 Nov 2026 Customer service agents: SOC 2, ISO 27001, GDPR and SSO ## Is LiteLLM yours? Free, and the page then carries the verified owner mark. You confirm it with an email at litellm.ai. [Claim this listing](https://agentsindex.ai/claim/litellm?from=owner-line) [Report an error](mailto:hello@agentsindex.ai?subject=Report%20an%20error%3A%20LiteLLM%20(litellm)&body=What%20is%20wrong%20on%20the%20page%2C%20and%20where%20on%20the%20product) if a fact is wrong.