OneTriangle (YC S26) @OneTriangleAI

The cheapest, fastest lightweight inference @hannah_chuu @medha_rv onetriangle.ai San Francisco, California Joined March 2026

Tweets

5
Followers

507
Following

3
Likes

16

Ankit Gupta @agupta

2 months ago

very smart team that made several key technical leaps in KV Cache optimization to stand up a competitive inference service.

@OneTriangleAI (YC S26) is building the fastest lightweight, cheap inference and hosting @deepseek_ai V4 Flash today at $0.15/M input and $0.35/M output tokens. Live at onetriangle.ai. Our group of @MIT grads and olympiad medalists from @GoogleDeepMind,

83 26 431 96K 163

4 6 225 55K 155

View Details

OneTriangle (YC S26) @OneTriangleAI

2 months ago

deepseek V4 flash, $0.15/M input and $0.35/M output

Hannah Chung @hannah_chuu

2 months ago

83 26 431 96K 163

3 1 9 3K 2

View Details

OneTriangle (YC S26) @OneTriangleAI

2 months ago

big things happening

Hannah Chung @hannah_chuu

2 months ago

We beat out @nvidia's KV cache transfer for KL divergence, and we're using it to build the fastest inference @TryTrustAI at @ycombinator. 17.8% less TTFT, $641 less per 1M requests, and 82.5% held-out top-1 agreement on Qwen 32B, prefilled from Qwen 8B.

15 19 147 20K 58

0 0 4 2K 2

View Details

Hannah Chung @hannah_chuu

2 months ago

15 19 147 20K 58

View Details

Hannah Chung @hannah_chuu

4 months ago

We’re in YC! Here’s what we’ve been up to: > Dropped out of MIT > Rejected our NYC quant and banking offers > Moved to SF > Fixed broken AI adoption with personalized one-click automations @TryTrustAI Excited to put everything into our product, great start to a new chapter.