Author's Description
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 multi-step reasoning to produce highly precise results 4x faster than any frontier model. It's designed to serve as a subagent that passes its findings to an "oracle" coding agent, who orchestrates/performs the rest of the coding task. To use relace-search you need to build an appropriate agent harness, and parse the response for relevant information to hand off to the oracle. Read more about it in the [Relace documentation](https://docs.relace.ai/docs/fast-agentic-search/agent).
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
The Relace Search model, designed for agentic multi-step reasoning in codebase exploration, demonstrates exceptional speed and competitive pricing. It consistently ranks among the fastest models and offers highly competitive pricing across all evaluated benchmarks. With a 96% success rate, its reliability is notably high, indicating minimal technical failures. In terms of performance across categories, Relace Search excels in its intended domain, achieving 91.0% accuracy in Coding, placing it in the 73rd percentile. It also shows strong performance in Mathematics (85.0% accuracy) and Ethics (96.0% accuracy). A significant strength is its complete absence of hallucinations, scoring 0.0% accuracy on the Hallucinations (Baseline) test, meaning it correctly identified all fictional concepts as "I don't know." However, its performance in General Knowledge (79.9% accuracy, 23rd percentile) and Email Classification (91.0% accuracy, 17th percentile) is comparatively lower. Instruction Following also presents a moderate weakness at 53.0% accuracy. Overall, Relace Search is a highly specialized and efficient tool for its specific use case, prioritizing precision and speed in code-related tasks.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $1 |
| Completion | $3 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Relace
|
Relace | relace/relace-search-20251208 | 256K | $1 / 1M tokens | $3 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by relace
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| Relace: Relace Apply 3 | Sep 26, 2025 | — | 256K |
Text input
Text output
|
— | — | $$$$ |