# Relace: Relace Search

Provider: relace  
Category: llm  
Model ID: `relace/relace-search`

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...

## Specs

- Context length: 256000 tokens
- Max output: 128000 tokens
- Modalities: text
- Released: 2025-12-08

## Pricing

- Input: $1.00 per million tokens
- Output: $3.00 per million tokens

## Providers

- **relace** — ctx 256000, input $1.00/M, output $3.00/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/relace-search