Relace Search

Relace · Released December 2025

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...

Facts and pricing

Provider

Relace

Context window

256K tokens

Input price

11.0 credits / 1M tokens ($1.00 raw)

Output price

33.0 credits / 1M tokens ($3.00 raw)

Vision (image input)

No

Tool calling

Yes

Extended reasoning

No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Relace Search now

What Relace Search is best for

• Balanced everyday work: writing, questions, brainstorming and summarization
• Long documents: the 256K-token window holds lengthy reports, contracts or papers whole
• Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows

Relace family

Frequently asked questions

What is Relace Search?

Relace Search is an AI model by Relace. 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...

How much does Relace Search cost on Zeplik?

Input tokens cost 11.0 credits per million and output tokens 33.0 credits per million (1 credit = $0.10; the raw provider rates are $1.00 and $3.00 per million). New accounts start with free credits.

How long can a conversation with Relace Search be?

Relace Search has a 256K-token context window (256,000 tokens), which covers the conversation plus any documents you attach.

Does Relace Search support images and tools?

Relace Search is text-only and supports tool calling.

Related models