Skip to content
LLMs
Relace logo

Relace: Relace Search

by Relace

Relace: Relace Search is a large language model from Relace. It costs $1.00 per million input tokens and $3.00 per million output tokens. Its context window is 256K tokens.

Tool callingStructured output
Input / 1M tokens
$1.00
Output / 1M tokens
$3.00
Cached input / 1M
-

Not supported

Context window
256K

tokens

Who serves it cheapest

1 hosts serve Relace Search. Same weights, same API - the price difference is pure margin and routing.

Providers serving Relace: Relace Search, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
RelaceCheapestbf16$1.00$3.00256K-100.0%

About 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...

Specifications

Relace: Relace Search specifications
Model IDrelace/relace-search
ProviderRelace
Context window256K tokens
Max output128K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsNo
ReleasedDecember 8, 2025

Cheaper alternatives

Models that cost less than Relace Search while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Relace: Relace Search cost?

$1.00 per million input tokens and $3.00 per million output tokens.

What is the context window of Relace: Relace Search?

256K tokens, with up to 128K tokens of output per request.