The home of open models, datasets and Spaces.
LiteLLM
Proxy and SDK to call 100+ LLM APIs in the OpenAI format.
SharkScore
#3 in Model APIs & inference
Why it scores 76.1
LiteLLM has a SharkScore of 76.1/100, ranked #3 of 262 in Model APIs & inference (updated 2026-11-19).
Each part compares LiteLLM with other listings in Model APIs & inference. Evidence covers 87% of the score's weight.
- Adoption
- 67 · 30%
- User reviews
- no data · 25%
- Maintenance
- 100 · 20%
- Trust & transparency
- 80 · 15%
- Momentum
- no data · 10%
Paying never changes this score. How ranking works · method v2026-11-18.2
RankShark review of LiteLLM
Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review
We were not paid for this review.
As of 2026-11-18, LiteLLM is an open-source, self-hosted gateway and Python SDK for routing requests across LLM providers; RankShark measured release v1.110.0 that day. [E1; MEASURED: latest release v1.110.0 on 2026-11-18]
LiteLLM provides an AI gateway and Python SDK for routing model requests through a common interface. Its pages describe spend tracking, access controls, guardrails, and self-hosted deployment. [E1]
Best for
- Platform teams that want a shared gateway with spend tracking, budgets, and access controls. · home page
- Developers building across multiple model providers through an OpenAI-compatible interface. · home page, docs
- Organizations that need to deploy the gateway in their own environment. · home page, docs
Not for
- Setups that require database-free enforcement of budgets or virtual keys; the docs say those functions require a database. · docs
Key features
- Shared model API. The vendor says the gateway provides an OpenAI-compatible API across 140+ providers and 1,800+ models. · home page
- Usage controls. The vendor says it tracks usage and spend, supports budgets and rate limits, and can stop requests at budget caps. · home page
- Routing and caching. The vendor says the gateway supports load balancing, lowest-cost routing, Auto Routing, response and semantic caching, and prompt compression. · home page
- Guardrails and logs. The vendor says it supports model access controls, guardrails, and audit logs on requests. · home page
- Self-hosted deployment. The vendor says the gateway can be self-hosted, including in air-gapped environments; its docs describe Docker and Kubernetes deployment options. · home page, docs
- Model catalog. The vendor's catalog lists 2,317 models across 113 providers, with prices and context windows. · pricing page
Pros
- The gateway offers a common interface for multiple providers, and the docs say OpenAI SDKs can call it by pointing the SDK at the gateway. · home page, docs
- The vendor lists controls for budgets, rate limits, model access, guardrails, and request logging. · home page
- The vendor documents self-hosting and deployment options including Docker, Helm, and Terraform. · home page, docs
Cons
- The docs say virtual keys and budget enforcement require a database; without one, budget limits are not enforced. · docs
- No public prices found on the pages we checked. · pricing page
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.
- Free plan
- Not stated (checked 18 Nov 2026)
- Free trial
- Not stated (checked 18 Nov 2026)
- Trains on customer data
- Not stated (checked 18 Nov 2026)
- Data retention
- Not stated (checked 18 Nov 2026)
- Data regions
- Not stated (checked 18 Nov 2026)
- Data processing agreement
- Not stated (checked 18 Nov 2026)
- AI models used
- The vendor's catalog lists 2,317 models across 113 providers, as of November 18, 2026. The gateway page separately advertises 1,800+ models across 140+ providers. · home page, pricing page
- SDKs
- Not stated (checked 18 Nov 2026)
- Webhooks
- Not stated (checked 18 Nov 2026)
- Platforms
- Not stated (checked 18 Nov 2026)
- Security claims
- Vendor states SOC 2 Type II. · docsThe vendor says its Docker images are signed with cosign and documents a command to verify signatures. · security pageThe vendor says it uses five security scanners in CI. · security page
What we measured
- GitHub stars · now
- 63,445
- Latest release · now
- v1.110.0 on 2026-11-18
- Package downloads · 30 days
- 98,646,196
- Tranco traffic rank · list of the day
- #65,974
How we tested · sources
- Hourly uptime and response-time checks of the product's URL.
- Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
- We did not sign up, pay, or use the product as a customer.
- home page: https://www.litellm.ai/ · fetched 18 Nov 2026
- pricing page: https://models.litellm.ai/ · fetched 18 Nov 2026
- docs: https://docs.litellm.ai/docs/proxy/docker_quick_start · fetched 18 Nov 2026
- changelog: https://docs.litellm.ai/release_notes · fetched 18 Nov 2026
- security page: https://www.litellm.ai/security · fetched 18 Nov 2026
Something wrong? Report an error with a public link that shows it; corrections re-run the review.
Top alternatives to LiteLLM
See all- 79.3ToolFreemium · from $9/mo
- 77.5
API for building with Claude models.
ToolPaid - 75.7
Google Cloud's platform to build with Gemini and other models.
ToolPaid - 75.3
API for GPT, image, audio and embedding models.
ToolPaid