Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Relace
relace/relace-searchCatalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
Relace 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...
Relace Search earns a request when it needs tool calls, very long inputs; a short, general request would go to Nemotron 3.5 Super VL (free) instead - free per million input tokens against $1.00 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points (this model has no published index).
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# targets.yaml - declare a target that runs Relace Search
targets:
- id: relace-search
kind: llm
name: Relace Search
metadata:
model: relace/relace-search # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 256000
cost:
usd_per_1k_tokens: 0.002000Input list price per million tokens; Relace Search is the most expensive of 2 listed.
Other models by the same vendor in the catalogue.
Photo: RDNE Stock project
A higher intelligence index, best first, with the price it comes at.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
