AI model · Relace
Relace Search
Model ID: relace/relace-search
- Input
- $1 per 1M tokens
- Output
- $3 per 1M tokens
- Context
- 256K tokens at once
- Max output
- 128K tokens per reply
- Released
- 8 Dec 2025 Relace
What it can do
- NoReasoning
- YesTool calling
- NoImage input
- NoOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
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...
Sources
- Relace: Relace Search on OpenRouter — read 2 Oct 2026