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...
With CoreAI, you can start chatting with Relace: Relace Search instantly — no separate subscription needed. CoreAI lets you chat with Relace: Relace Search alongside 300+ other AI models from Relace and other providers like OpenAI, Anthropic, Google, Meta, and more.
Measured against all 392 chat models CoreAI serves, Relace: Relace Search sits at #213 for context capacity — 256K tokens, roughly 192,000 words or 384 pages of text in a single conversation. On price, it is the #114 cheapest of 183 standard-tier models by input cost. It joined the catalog on 2025-12-08.
Every model in this table is available on CoreAI — open the web app and run the same prompt through Relace: Relace Search and Relace: Relace Apply 3 side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00250 on Relace: Relace Search's raw per-token rates; a heavy session with a 50K-token document costs about $0.065. On CoreAI you don't juggle these numbers — one subscription covers Relace: Relace Search and 300+ other models under a plan usage limit, with no API keys. See plans.
Relace: Relace Search handles 256K tokens of context — roughly 192,000 words, or about 384 pages of text in one conversation.
Relace: Relace Search's underlying rates are $1 per 1M input tokens and $3 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
No — Relace: Relace Search is text-only. If you need image understanding, its standard-tier peers with vision are listed in the comparison table above.
No — Relace: Relace Search answers directly without an extended reasoning phase, which usually means faster responses.
Open the CoreAI web app or the iOS/Android app, pick Relace: Relace Search in the model selector, and chat — no API key, no per-token billing. One subscription covers Relace: Relace Search and 300+ other models.
The closest alternatives on CoreAI are Relace: Relace Apply 3, Kwaipilot: KAT-Coder-Pro V2.5, inclusionAI: Ling-2.6-flash — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with Relace: Relace Search and 300+ other AI models — all in one app.