LiteLLM
MIT-licensed, self-hosted proxy exposing an OpenAI-compatible API in front of 100+ LLM providers, by BerriAI.
LiteLLM's open-source proxy has no usage fee or model markup. You use your own provider keys and run the proxy yourself. Hosting it in the EU does not by itself keep downstream model calls there; check each provider too. SSO/SAML, audit logs, multi-team management and guardrails require an Enterprise edition with no public price.
- Headquarters
- 🇺🇸 United States
- Parent jurisdiction
- 🇺🇸 United States (parent: BerriAI)
- EU self-serve plan
- Available; check eligible plans and regions
- GDPR DPA
- No / not documented
- Billing
- self-hosted
- Free tier
- Open-source proxy is free to self-host.
- Open source
- Yes · self-hostable
- Website
- www.litellm.ai
- Source last checked
- 2026-10-06
- Pricing evidence
- Operating cost not estimated
Pricing
Operating cost not estimated · servers, licenses and engineering time are yours. See notes for software editions and license terms.
Budget for proxy hosting and maintenance, plus your model-provider bills (always your own keys, no markup). The proxy runs where you deploy it; downstream model processing depends on each provider's region. Enterprise edition (SSO/SAML, audit logs, multi-team management, guardrails) needs a sales quote, with no public price. No vendor DPA applies to the open-source proxy itself because the vendor does not process its traffic.
Managed alternatives
At $10,000 model spend / month. Adjust usage and requirements.
LiteLLM has no bill to estimate: you pay for the servers, storage and time to run it. Vercel AI Gateway is free at this usage, so running LiteLLM yourself only makes sense for control or features, not cost.
- Vercel AI Gateway: $0/yr estimatedPublished rates
- Portkey: $588/yr estimatedModeled ratesShows the base Production fee only; logged-request overages are not modeled by the model-spend input.
- Helicone: $948/yr estimatedModeled ratesShows the subscription fee; request, storage and other usage-dependent extras are not modeled by the model-spend input.
- Cloudflare AI Gateway: $6,000/yr estimatedModeled ratesUnified Billing fee only; BYOK avoids it. Log storage and Logpush overages are excluded.
- Requesty: $6,000/yr estimatedPublished rates
No cheaper managed estimate matches your filters. Adjust your usage or compare with your actual contract bill.
The price difference leaves out migration costs, operating costs and any features you’d need to replace.
Self-hosted options
Operating cost is not estimated. These options are not counted as savings against managed services.
Compare LiteLLM
Found a wrong rate or plan restriction? Report a correction with a current source.