AI Observatory / Model Radar
Relace / relace/relace-search
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...
256,000
Context
128,000
Max output
$1.00 / 1M
Prompt price
2025-12-08
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Relace | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $1.00 / 1M |
| Completion price | $3.00 / 1M | Request price | N/A |
| Context length | 256,000 | Max completion tokens | 128,000 |
| Supported parameters | max_tokens, seed, stop, temperature, tool_choice, tools, top_p | ||
Best for
relace/relace-search
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...
Coding workflows
Long context
High-volume usage
tool-capable
long-context
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.