modelgrep
R

Relace: Relace Search

relace/relace-search

Tools
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
13
281st fastest
Latency
652ms
first token
Input price
$1.00
205th cheapest
Context
256K
128K max out

How it compares

Faster than5%
of all ranked models
Cheaper than31%
of all ranked models

Overview

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...

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Relacebf16$1.00$3.00

Specifications

Context window256K
Max output128K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Relace Search FAQ

How much does Relace Search cost?

Relace Search costs $1.00 per million input tokens and $3.00 per million output tokens via OpenRouter, making it 205th cheapest of 298 paid models.

How fast is Relace Search?

Relace Search generates around 13 tokens per second with 652ms time-to-first-token (p50), the 281st fastest tracked model.

What is Relace Search's context window?

Relace Search supports a 256K-token context window and can output up to 128K tokens. It accepts text input.

Compare head-to-head