Launching today
Auriko
Trading desk for LLM calls
308 followers
Trading desk for LLM calls
308 followers
Auriko treats LLM providers as trading venues and arbitrages the spread. Built by ex-quant traders, Auriko’s cost-arbitrage engine calibrates to each user’s request patterns and selects optimized inference paths based on token price, cache behavior, latency, reliability, and request quality. Auriko benchmarks show average 30% cost reduction against industry peers and direct providers. See the source: https://www.auriko.ai/reports/llm-cost-arbitrage
A trading-desk framing for LLM calls makes sense. Once teams have more than one model and more than one workload, the real work becomes routing, cost control, and knowing why a call behaved the way it did. The audit trail matters as much as the cheaper token path.
The quality bar for production AI apps is high, so cache aware routing needs good observability.
I like that the focus is not just more models, but using the right route for each request.
someone on my team has been comparing different inference providers manually to keep costs under control. I'll definitely share Auriko with them because it could save a lot of effort.
Typeless
This looks super useful for teams watching their AI bill climb every month. Congrats!
Auriko
@yuki1028 Thanks!
@zxy_action1 Michael... this is jaw-dropping. I am beyond impressed by such a novel yet robust approach to token-spend reduction. My budget loves this!
(my brain, however...? it immediately wants to set about reverse-engineering this mf to tune it towards revenue generation... 😈)
Great work!!
Auriko
@grey_seymour Glad you like it!
Pokecut
Congrats on the PH launch! Modeling request patterns sounds helpful.