LLM Gateway
An LLM API gateway for routing requests across providers with caching, failover and usage analytics.
About LLM Gateway
Developers need to switch model providers and track inference costs without maintaining separate integrations for each provider.
Who it’s for
- Developers integrating multiple model providers
- Platform teams tracking model usage and costs
When to consider it
Consider LLM Gateway when you want an OpenAI-compatible gateway with provider routing, request caching and cost visibility.
Tradeoffs & limitations
- Bring-your-own-key routing has no platform fee, but you pay providers directly; buying gateway credits incurs a 5% fee.
- The core is AGPLv3 licensed; production use of code in the ee/ directory requires a valid Enterprise license.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use LLM Gateway.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Oct 13, 2026 · Prepared with AI assistance; not a hands-on benchmark.
- Official gateway overview
- Provider billing and gateway credit fees
- Official repository overview
- Core license terms
- Enterprise production license terms
- OpenAI-compatible Decisions API — October 12, 2026
- Official product touch icon
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
LLM Gateway official website
An LLM API gateway for routing requests across providers with caching, failover and usage analytics.
Based on official pages and announcements checked on 2026-10-13. No hands-on test, performance benchmark or popularity ranking is claimed.
