Relace Launches: Cheaper, Faster, and More Reliable AI Code Generation

Relace recently launched!

‍

^{"Kicking off with Instant Apply, Code Reranker, and Embeddings."}

^‍

^{TL;DR: Relace models are designed to slot naturally into most AI codegen products, making them faster, cheaper, and more reliable. They already have SOTA:}

‍

^{• Embedding + Code Reranker models to retreive the relevant context from million-line codebases in ~1-2s.}

‍

^{• Instant Apply model that merges code snippets at >2500 tok/s.}

‍

^{Relace is in production with Lovable, Magic Patterns, Codebuff, Create, Tempo Labs, and 20+ other AI codegen startups. Watch the Instant Apply model race against full file rewriting with Claude 3.7 Sonnet:}

‍

^{https://www.youtube.com/watch?v=J0-oYyozUZw}

‍

Founded by Preston Zhou & Eitan Borgnia‍‍

Hey everyone 👋 Meet Preston and Eitan, the cofounders of Relace.

‍

Problem

Agentic coding systems are easy to prototype, but hard to make robust. As users succeed at creating more complex designs/applications, you hit bottlenecks:

• Larger codebases require efficient context management -- you can't pass everything to the AI agent.
• Slow and expensive full file rewrites need to be replaced with abbreviated diff formats.

Frontier models (like Claude 3.7, o3, etc.) are powerful, but overkill for these auxiliary functions like retrieval and merging. Costs start to add up, especially when every agent action hits an API with thousands of tokens in and out. Plus, non-technical users are easily frustrated by high latency, especially if they are trying to refine small aspects of the code they created.

‍

Solution

Relace models are trained to achieve order-of-magnitude improvements in both latency and cost without compromising on accuracy.

Instant Apply:

Released in February, this model merges semantic code snippets at 2,500 tokens/sec with an average end-to-end latency of ~900ms across Relace users.

Inspired by Cursor's Fast Apply, the semantic diff format is chosen to be natural for all models to output. A simple prompt change combined with Instant Apply can reduce Claude 3.5/3.7 token usage by ~40%.

Relace trains on hundreds of thousands of code merges across dozens of different coding languages to achieve SOTA accuracy:

‍

Embeddings and Reranker:

The embedding model + reranker can determine the relevance score for a user request against million-line codebases in ~1-2s. By training on hundreds of thousands of query/code pairs, Relace can effectively filter out irrelevant files and cut input token usage by over 50%.

‍

Not only does this save on cost, but cleaning up the context window significantly improves generation quality of the AI agent.

‍

Try It Out

Both of these models are battle tested and running millions of times a week in production. You can read more and try it out for yourself with the links below.

‍

Learn More

‍

^{🌐 Visit www.relace.ai to learn more.}

^‍

^{👉 App: app.relace.ai. Docs: docs.relace.ai. There is a free tier for small projects, and the founders offer discounted rates for open source partners like their friends at Continue.}

^‍

^{🤝 Don't hesitate to reach out if you're optimizing your coding agent — the founders would love to hear your thoughts, feedback, and what you're building!}

^‍

^{👣 Follow Relace on LinkedIn.}

‍