Relace Searchon Krater.ai

The relace-search model uses 4-12 viewfile 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

Released December 8, 2025

Specifications

Relace Search at a glance

Context

256K tokens

Max output

128K tokens

Input

Text

Output

Text

Input price

$1.00 / 1M

Output price

$3.00 / 1M

Tool calling

Capabilities

What it is good at

Catalog capabilities

  • Generates text responses
  • Supports tool calling

Good for

Long documentsUse with tools

FAQ

Questions about Relace Search

Clear answers based on the model catalog and Krater access.

Relace Search supports a context window of 256,000 tokens.

Use Relace Search in your API

Connect with Krater's unified API.

API access

Ready to use Relace Search?

Access leading models in one focused workspace.