relaceListed Dec 8, 2025

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 window256K
Max output128K
Provider endpoints2
Benchmark results0
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

2 quotes

Relace

via OpenRouter

relace/bf16 · quantization=bf16

Input
$1.00
Output
$3.00
USD / 1M tokens
256K context128K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDrelace/relace-search::relace/bf16

Model specifications

Developer
relace
Modality
Language
Context
256,000 tokens
Maximum output
128,000 tokens
Weights
Not reported
Provider listed
Dec 8, 2025
First discovered
Oct 16, 2026

Exact identities

  • openrouterrelace/relace-search

Sources

Updated Oct 17, 2026

More from relace

View all ↗
relaceListed Sep 26

Relace: Relace Apply 3

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...

256K contextNo reported score
No reported score
$0.85in$1.25out/ 1M tokens · USDRelace · via OpenRouter · 2 endpointsrelace/fp8 · quantization=fp8