Relace: Relace Search: AI model
Relace Search is an agentic code-search model that uses parallel file-view and grep tools to find the most relevant files for your request. Reachable from inside Iran through Hormouz.
- Context window:
- 256,000 tokens
- Input:
- $1/1M tokens
- Output:
- $3/1M tokens
- Type:
- text
- Tools
- Streaming
- Long context
Relace Search is an agentic code-search model that explores a codebase using parallel file-view and grep tools and returns the most relevant files for the user’s request.
Unlike traditional retrieval, Relace Search performs agentic multi-step reasoning to produce highly precise results, and it can serve as a subagent that hands its findings to a primary coding agent. Its context window is up to 256K tokens, and access runs through Hormouz behind an OpenAI-compatible API.
Pricing is usage-based: $1.00 per million input tokens and $3.00 per million output tokens. Hormouz provides stable access to the model from inside Iran.
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...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "relace/relace-search",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Relace |
|---|---|
| Type | Text |
| Context window | 256,000 tokens |
| Pricing | $1.00/M in · $3.00/M out |
| API | Chat Completions |
| Capabilities | Streaming · Tools |
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "relace/relace-search",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="relace/relace-search",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "relace/relace-search",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Relace: Relace Search API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Relace: Relace Search and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Relace Search cost?
- Billing is usage-based: $1.00 per million input tokens and $3.00 per million output tokens.
- How do I access Relace Search from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
- Is Relace Search compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
- How does Relace Search work?
- It uses parallel file-view and grep tools with agentic multi-step reasoning to find the most relevant files in a codebase.
- What is Relace Search good for?
- It is designed as a search subagent that hands its findings to a primary coding agent; its context window is up to 256K tokens.
Updated 2026-10-13