---
title: "More than 100x Faster & Cheaper LLM-Powered SQL Queries with Proxy Models"
url: https://daily.dev/posts/more-than-100x-faster-cheaper-llm-powered-sql-queries-with-proxy-models-9p5lkyzgg
source_url: https://cloud.google.com/blog/products/data-analytics/more-than-100x-faster-and-cheaper-llm-powered-sql-queries-with-proxy-models
type: article
source: "Google Cloud"
published: 2026-05-13T16:04:41.552Z
updated: 2026-05-13T16:05:05.023Z
tags: ["llm", "nlp", "sql", "google-bigquery", "alloydb"]
reading_time: 11
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# More than 100x Faster & Cheaper LLM-Powered SQL Queries with Proxy Models

**[Google Cloud](https://daily.dev/sources/gcp)** · 11 min read · 0 upvotes · 0 comments

## Summary

Google Cloud researchers present proxy models, a technique to dramatically reduce the cost and latency of LLM-powered SQL functions in databases like BigQuery and AlloyDB. Instead of calling an LLM for every row, proxy models use lightweight classifiers (e.g., logistic regression) trained on Gemini embeddings to replace most LLM calls. The system automatically samples data, labels it with an LLM, trains a proxy, evaluates its quality, and decides whether to use the proxy or fall back to full LLM inference. Benchmarks across 11 datasets show proxy models achieve 90–116% of LLM accuracy while consuming ~400x fewer tokens and reducing query latency by 30–100x. The technique is already live in BigQuery and AlloyDB via the 'optimized mode' for AI.IF and AI.CLASSIFY functions.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://cloud.google.com/blog/products/data-analytics/more-than-100x-faster-and-cheaper-llm-powered-sql-queries-with-proxy-models>

## Similar posts on daily.dev

- [AlloyDB Ships Proxy Models That Replace LLM Calls with Local Inference Inside the Database](https://daily.dev/posts/alloydb-ships-proxy-models-that-replace-llm-calls-with-local-inference-inside-the-database-4vvzzcrji) · InfoQ · 1 upvotes · 0 comments
- [The new database world according to Google: Inexact queries and AI in everything](https://daily.dev/posts/the-new-database-world-according-to-google-inexact-queries-and-ai-in-everything-asxnk5xfw) · DEVCLASS · 2 upvotes · 0 comments
- [Your Data Model Is the Semantic Layer](https://daily.dev/posts/your-data-model-is-the-semantic-layer-ro8bktzht) · MotherDuck · 0 upvotes · 0 comments

---

Tags: [#llm](https://daily.dev/tags/llm), [#nlp](https://daily.dev/tags/nlp), [#sql](https://daily.dev/tags/sql), [#google-bigquery](https://daily.dev/tags/google-bigquery), [#alloydb](https://daily.dev/tags/alloydb)

[View this post on daily.dev](https://daily.dev/posts/more-than-100x-faster-cheaper-llm-powered-sql-queries-with-proxy-models-9p5lkyzgg)
