# Exa cuts document-embedding costs 47% on AWS chips

> Exa says software and kernel changes lifted embedding throughput on AWS Inferentia2 and Trainium2, reducing its cost per million documents by 47%.

Oossa · 2026-11-19 · https://oossa.com/en/exa-cuts-document-embedding-costs-47-on-aws-chips

Exa says it improved its document-embedding system on AWS Inferentia2 and Trainium2 chips, which it uses to prepare web pages for semantic search. The company reports a 47% improvement in both performance and cost per million documents compared with its initial setup.

Its work included custom attention and neural-network kernels, plus changes to memory use. Exa says it validated outputs against its reference model using a 0.999 cosine-similarity threshold; it did not report a change to its search product or customer pricing.

## The facts

- Exa selected 30 billion high-priority documents for re-embedding.
- The final system improved performance and cost per million documents by 47% against Exa’s initial baseline.

## Why it matters

For Exa, lower embedding cost per million documents can make maintaining an index of billions of pages less expensive; the company did not say whether customers will see a price or service change.

## Sources & references

1. [Exa boosts embedding throughput by 50% to index billions of documents on AWS AI chips](https://aws.amazon.com/blogs/machine-learning/exa-boosts-embedding-throughput-by-50-to-index-billions-of-documents-on-aws-ai-chips/) – AWS, 2026-11-18

Last updated: 2026-11-19
