Relace Search
Relace Search is a specialized model developed by Relace designed to navigate and analyze codebases. It functions by using parallel file exploration tools to identify and retrieve relevant information for user queries.
Relace Search specs and pricing
- Provider: Relace
- Released: December 8, 2025
- Context window: 256K tokens
- Max output: 128K tokens
- Input: text
- Output: text
- Price: $1.00 input / $3.00 output per 1M tokens
- Tool calling: yes
What Relace Search is good at
- Searching through large software repositories
- Locating specific code definitions or patterns
- Analyzing complex project structures
To-dos to try with Relace Search
- Find all files in this repository that define the authentication middleware.
- Identify where the database connection string is configured across the codebase.
- Locate the function responsible for processing user uploads in the backend directory.
FAQ
- How does Relace Search find information in a codebase? It uses parallel 'view_file' and 'grep' tools to explore files rather than relying on traditional RAG methods.
- What types of input and output does this model support? Relace Search is designed to process and generate text-based content.
- How much does Relace Search cost? Relace Search costs $1.00 per million input tokens and $3.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 3.22 credits ($1 = 100 credits).
- What is the context window of Relace Search? Relace Search can read up to 256K tokens at once and write up to 128K tokens in one reply.
- Can I use Relace Search without coding? Yes. In todo.is you pick Relace Search as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.