relace

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...

Context
256k tokens
Input / 1M tokens
$1
Output / 1M tokens
$3
Benchmark

Pricing

Input tokens$1 per 1M tokens
Output tokens$3 per 1M tokens

Technical details

Model IDrelace/relace-search
Context window256k tokens
Input modalitiestext
Output modalitiestext
TokenizerOther
Max output tokens128,000

Use with MegaBrain

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://getmegabrain.com/api/gateway/v1',
  apiKey: process.env.MEGABRAIN_API_KEY,
})

const response = await client.chat.completions.create({
  model: 'relace/relace-search',
  messages: [{ role: 'user', content: 'Hello!' }],
})

Ready to use Relace: Relace Search?

Get an API key and start making requests in minutes.

Get an API key