Launched this week
Liquid Inference
LLM router where providers compete for every prompt
64 followers
LLM router where providers compete for every prompt
64 followers
* Fully compatible with agentic coding tools: Claude Code, Codex, OpenCode, Cursor, Pi, Cline, and many more. Full multi-modal support. * Hundreds of open- and closed-weight models. Create routing rule presets or use our Auto routing algorithms. * Providers compete dynamically on price for every prompt, offering the lowest marginal cost. * Sign up for free with email, first 500 users get $20 of free inference. Receive 20% of referred fees as free inference, 10% for second-level referrals.
Free
Launch Team
EneyProactive AI for Mac. Free test, 20,000 credits.
Promoted
Having so many models behind one router could make choosing the right model a lot less of a headache.
Congrats on the launch, Brett! Having providers compete on each request is an interesting way to price inference. I like that developers can keep their existing coding tools while trying it.
@brett_harrison_architect Congrats on the launch, Brett! I run three providers with fallback for customer-facing copy, so this caught my eye. My worry is tone changing if the cheapest provider changes between calls. Can I pin one model for a task and let price routing handle the rest?