BerriAI

license

MIT(core)

enterprise-dir

LiteLLM-Commercial-License

source

public

core features withheld

yes — the enterprise/ directory ships under the proprietary BerriAI Enterprise License requiring a paid subscription for production use, and the proxy gates premium features on a LITELLM_LICENSE key verified against license.litellm.ai

LiteLLM's MIT core is genuinely open, but the enterprise/ directory ships its own hooks, UI and deployment stack under a separate proprietary BerriAI license that requires a paid, seat-counted subscription before production use. A license key checked against BerriAI's server enforces the gate, which is what makes LiteLLM open core rather than fully open.

• https://api.github.com/repos/BerriAI/litellm recorded 2026-08-11

  Repository root. The published tree is the whole gateway and proxy - litellm, gateway, ui, backend, helm, terraform, docker, migrations, tests - and self-hosting it needs nothing that is not in the repo, so the source dimension is public. Retained from the phase-C pass with a real reading in place of the placeholder.

• https://api.github.com/repos/BerriAI/litellm/contents/enterprise recorded 2026-08-11

  The carved-out directory exists and is not a stub. It contains LICENSE.md, README.md, __init__.py, cloudformation_stack, dist, enterprise_hooks, enterprise_ui, litellm_enterprise and its own pyproject.toml - hooks, a UI and a deployment stack, i.e. shipped functionality. The repository license endpoint returns NOASSERTION rather than MIT, which is GitHub declining to classify the split root LICENSE.

• https://cdn.jsdelivr.net/gh/BerriAI/litellm@main/enterprise/LICENSE.md recorded 2026-09-29

  The enterprise license body, read through the jsDelivr mirror. It says the software "may only be used in production, if you (and any entity that you represent) have agreed to, and are in compliance with, the BerriAI Subscription Terms of Service" and also allows copying and modifying "for development and testing purposes, without requiring a subscription".

• https://cdn.jsdelivr.net/gh/BerriAI/litellm@main/LICENSE recorded 2026-09-29

  The root LICENSE file, read through the jsDelivr mirror of the repository. It opens "Portions of this software are licensed as follows:" and splits the tree in two: the "enterprise/" directory falls under its own license, and content elsewhere "is available under the MIT license as defined below".

• https://cdn.jsdelivr.net/gh/BerriAI/litellm@main/litellm/proxy/auth/litellm_license.py recorded 2026-09-29

  The license check module, read through the jsDelivr mirror. Its header comment is "If litellm license in env, checks if it's valid", LicenseCheck reads the key with os.getenv("LITELLM_LICENSE", None), and the is_premium method returns False when no key is set, so features tested against it run only with a valid key.

• https://cdn.jsdelivr.net/gh/BerriAI/litellm@main/pyproject.toml recorded 2026-09-29

  The pyproject.toml of the package, read through the jsDelivr mirror. It declares license = "MIT" for the litellm package and points its Repository entry at "https://github.com/BerriAI/litellm".

• https://cdn.jsdelivr.net/gh/BerriAI/litellm@main/README.md recorded 2026-09-29

  The repository README, read through the jsDelivr mirror. Its contributing steps run "git clone https://github.com/BerriAI/litellm.git" and then "make install-dev", so the gateway builds from the public tree, and its Enterprise section lists "Features under the [LiteLLM Commercial License]" as the paid tier.

• https://docs.litellm.ai/docs/enterprise recorded 2026-09-29

  The Enterprise page of the LiteLLM docs, which separates the open-source proxy from the paid tier: "SSO is free for up to 5 users. Beyond that, an enterprise license is required." and "Built-in moderation callbacks need a license". It also says "A license key enables the features above", with the key set as LITELLM_LICENSE.

• https://raw.githubusercontent.com/BerriAI/litellm/main/enterprise/LICENSE.md recorded 2026-08-11

  The enterprise license body. It states the software "may only be used in production, if you (and any entity that you represent) have agreed to, and are in compliance with, the BerriAI Subscription Terms of Service ... or other agreement governing the use of the Software, as agreed by you and BerriAI, and otherwise have a valid BerriAI Enterprise license for the correct number of user seats". Copying for development and testing is allowed; "it is forbidden to copy, merge, publish, distribute, sublicense, and/or sell the Software". Production use behind a seat-counted paid license is functionality withheld from the MIT source.

• https://raw.githubusercontent.com/BerriAI/litellm/main/LICENSE recorded 2026-08-11

  Root LICENSE body, read rather than assumed. It opens "Portions of this software are licensed as follows:" and then splits the repository in two - "All content that resides under the 'enterprise/' directory of this repository, if that directory exists, is licensed under the license defined in 'enterprise/LICENSE'" and "Content outside of the above mentioned directories or restrictions above is available under the MIT license as defined below", followed by the full MIT text. So the tier-setting license is MIT and the gate is a carve-out named in the license itself.

• https://www.litellm.ai/ recorded 2026-06-04

  Vendor site, kept for context only. It establishes that BerriAI sells a hosted product, which under the settled rule is NOT evidence for or against core-gated and is not what the open-core reading is based on.

Adoption is measured by PyPI downloads of the litellm package, which land far above the mass-market threshold. Much of that volume comes from continuous-integration pipelines that install litellm on every run touching a model provider, rather than from direct end-user installs.

• https://github.com/BerriAI/litellm recorded 2026-08-15

  Repository page for BerriAI/litellm: 56.4k stars and 10.6k forks. Corroboration only; the measured PyPI count in the source above it is the adoption figure, not stars.

• https://pypistats.org/api/packages/litellm/recent recorded 2026-08-13

  741,403,911 downloads in the trailing 30 days for litellm; 207,823,088 weekly and 28,463,811 daily

LiteLLM is a unified gateway to a very large set of LLM providers in OpenAI format, with cost tracking, guardrails, load balancing, virtual keys, budgets and logging. No standard benchmark applies to a gateway, so this is rated on the breadth of provider coverage and production features it ships.

• https://docs.litellm.ai/ recorded 2026-09-29

  The LiteLLM docs home page, headed "Call 100+ LLMs using the OpenAI Input/Output Format": it lists translation to /chat/completions, /responses, /embeddings, /images, /audio and /batches, "Retry/fallback logic across multiple deployments (e.g. Azure/OpenAI)", and "Track spend & set budgets per project" through the proxy server, with a Python SDK alongside.

• https://github.com/BerriAI/litellm recorded 2026-08-15

  Repository page describing the gateway: a single interface over many provider endpoints, with routing, fallbacks and spend tracking.