Model comparison
Relace Search vs Gemini 2.5 Pro
Capability radar, value bars, and side-by-side posture.
Relace Search
Not scored
value score
Gemini 2.5 Pro
93
value score
Relace Search ctx
—
Gemini 2.5 Pro ctx
1.0M
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Gemini 2.5 Pro93
Attribute tape
| Field | Relace Search | Gemini 2.5 Pro |
|---|---|---|
| Developer | Relace | Google DeepMind |
| Context | — | 1.0M |
| Modalities | Text, Code, Image, Audio, Video | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $1.25/1M in · $10/1M out |
| Value score | — | 93 |
| Summary | Relace Search is a codebase search subagent model that explores repositories using multiple parallel file-read and grep tool calls, then returns the most relevant files or code context for downstream coding agents. It is purpose-built for agentic multi-step repository exploration rather than general-purpose chat or standard RAG retrieval. | Google frontier multimodal model. |