Loading page
Loading page

AI · OpenRouter alternative
Put one OpenAI-compatible endpoint in front of 100+ LLM providers, with virtual keys, spend tracking and load balancing.
LiteLLM is an open-source AI gateway. It gives you one interface for more than 100 LLM providers, all in the OpenAI request format. This template runs the proxy server, which sits between your apps and the providers.
Your apps talk to LiteLLM as if it were OpenAI. LiteLLM forwards each call to the right provider, records the spend, and applies your rules. Those rules include virtual keys, fallbacks, guardrails and load balancing.
LiteLLM suits engineering teams that use more than one model provider. It also fits platform teams who must give many developers access to LLMs without handing out the master API keys.
Hosted gateways see every prompt and response that passes through them. A self-hosted LiteLLM keeps prompts, logs and provider keys in your own service, with a PostgreSQL database for keys and spend data.
The trade-off: the gateway becomes a point that all AI traffic depends on. Keep LITELLM_MASTER_KEY secret, watch the logs, and keep backups of the database. You still pay each provider for the tokens you use. You look after updates yourself.
Containers: ghcr.io/berriai/litellm:main-latest, postgres:16-alpine
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose LiteLLM, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the LiteLLM setup screen.