Relace Search

About 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 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).

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Relace Model Lineup

Compare all models from Relace to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Nova Pro 1.0

Amazon

Input: $0.80

Output: $3.20

Context: 300k

Hermes 4 405B

Nous Research

Input: $1.00

Output: $3.00

Context: 131k

MiMo-V2.5-Pro

Xiaomi

Input: $1.00

Output: $3.00

Context: 1.1M

Qwen VL Max

Alibaba Qwen

Input: $0.80

Output: $3.20

Context: 131k

💡 Cheaper Alternatives

Same Brand (Relace)

Cross Brand

🚀 Quick Start

Get started with Relace Search API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="relace/relace-search-20251208",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision