All AI models · LLM benchmarks · Methodology

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...

Model facts

Context window
256K tokens
Maximum output
128K tokens
Cheapest paid input
$1 per 1M tokens
Cheapest paid output
$3 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

tool calling, temperature control, text.

Observed price history

  • 2026-08-24: $1 input / $3 output per 1M tokens

API providers