Launching today
BaseLLM
Self-hosted AI gateway with budgets, limits and audit logs
1 follower
Self-hosted AI gateway with budgets, limits and audit logs
1 follower
Control all your company's AI traffic from your own servers. Apps call one OpenAI-compatible endpoint; BaseLLM routes to any model and enforces limits, USD budgets, secret scanning and PII masking before the call, with a tamper-proof audit log.



Launch Team

AWS Activate CreditsCredits that fuel your startup’s next milestone
Promoted
Hi Product Hunt! 👋 I'm Ramazan from the BaseLLM team.
We built BaseLLM because the companies we work with, especially banks and other regulated teams, wanted to use LLMs but couldn't send traffic straight to providers without control. Every team was wiring up its own keys, nobody knew the monthly bill until it arrived, and there was no reliable record of who sent what.
BaseLLM sits between your apps and the models, on your own infrastructure:
• One OpenAI-compatible endpoint for OpenAI, Anthropic, Gemini, OpenRouter and in-house models
• Limits per project, API key, user and model, plus monthly USD budgets with a month-end forecast
• Secret scanning on every request and personal data masking
• A tamper-proof audit log you can export to your SIEM
• Works with Claude Code and the Anthropic SDK too
All checks run before the model is called, so a rejected request never costs you anything.
We'd love your feedback, especially if you run LLMs in a regulated environment: what would you need from a gateway like this before rolling it out company-wide?