AI Gateway tool profile
LLM Gateway
An open-source (AGPLv3) LLM API gateway for 200+ models across 40+ providers, available hosted with a 5% fee on purchased credits or free to self-host, with smart routing between cheap and frontier models.
Independent research from official sources · Sources · How we review
- Best for
- Developers who want an OpenRouter-style hosted gateway with no fee on their own provider keys, or the option to self-host the same open-source code.
- Starting point
- Free: $0, 3 zero-cost models (20 requests a minute), 5% platform fee on credit purchases, no platform fee...
- Free plan
- Yes — Free plan at $0 with no credit card: 3 zero-cost models at 20 requests a minute and 30-day data retention.
- Key limitation
- AGPLv3 license: modifying and offering it as a network service obliges you to publish your changes
Choose it if
Strongest for
Built for
Avoid it if
- Smaller project than OpenRouter or LiteLLM (about 1.7k GitHub stars)
- The free plan's zero-cost models are rate limited to 20 requests a minute
Free-plan suitability
Free plan at $0 with no credit card: 3 zero-cost models at 20 requests a minute and 30-day data retention; paid models use purchased credits (5% fee) or your own keys (no fee).
Pricing
Free: $0, 3 zero-cost models (20 requests a minute), 5% platform fee on credit purchases, no platform fee when you bring your own provider keys, 30-day data retention; optional payload storage at $0.01 per 1M tokens. Enterprise: custom (30-day trial, volume discounts, 99.9% uptime SLA, SSO/SAML, audit logs, guardrails). Self-hosting is free under AGPLv3.
Verify the current plan, credits, output limits, and commercial terms before purchasing.
Run it 24/7 on your own server
LLM Gateway runs on your own machine, so it stops answering when your laptop sleeps. A small Linux VPS with Docker keeps it online for scripts, agents and teammates, with a fixed monthly cost instead of per-token markup.
- Start with the smallest plan that runs Docker; upgrade only if you add users or local models.
- Keep the gateway bound to localhost or behind a firewall, and store provider keys as environment variables.
- Monthly billing lets you test before committing to a long term.
Some links are affiliate links. We may earn a commission if you buy through them. Payment never changes our rankings or editorial verdicts.
What LLM Gateway does
- One OpenAI-compatible API for 200+ models across 40+ providers, with several providers per model
- Smart Routing (September 25, 2026): a classifier sends easy prompts to a cheap model and hard ones to a frontier model you allow
- Bring your own provider keys with no platform fee, or buy credits with a 5% fee
- Request analytics and optional full-payload storage
- AGPLv3 code on GitHub (about 1.7k stars, release v1.20.0 on 2026-10-05) for self-hosting
Is it legit?
Who is behind LLM Gateway, where it is based, and what is publicly known about its funding. Company details change — verify on the official site before committing.
- Company
- Polar Lights LLC
Evaluation guide
Step-by-step evaluation guides for LLM Gateway — workflow fit, pricing, rights, and a same-input test before paying.
Where LLM Gateway appears
Best-of lists and roundups that include LLM Gateway.
Official sources
These links are retained beside the catalog record so changing details can be rechecked.