Update: Now in Closed Beta

The dedicted AI that improves over time.

Interlace makes LLMs radically cheap, easy, performant. Switch your API key to ours, and we'll do the rest.

Join Waitlist

Two lines of code.
Incredible results.

30x cheaper inference...
...that performs better than GPT

GPT-4 Turbo
GPT-3

$0.0015/M tokens
$0.0002/M tokens

Tentative closed beta pricing, subject to change.

Interlace Personalized Model93%

OpenAI GPT-482%

Across all clients in beta as of February 10th, 2024.

10x faster

Interlace models generate tokens much faster, giving you quality LLM responses faster.

Interlace Personalized Model560 t/s

OpenAI GPT-445 t/s

Tested on client working on docker streamlining. Inference on A100 80G.

Build the LLM projects of tomorrow.
Available Soon.

Interlace Team 2024