Two lines to welcome a shop in Oran.
Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.
Try in Chat Labby Relace·Released 26 September 2025
Relace Apply 3 merges a suggested code change into your file. You send the instruction, the original code and the edit snippet in that set layout, and it returns the updated file, working through a file of up to about 250 pages. The edit can come from another AI such as GPT-4o or Claude.
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 282,91 DA | 416,04 DA |
per 1M tokens
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Latency | Throughput | Uptime |
|---|---|---|---|---|---|
| Relace | 282,91 DA | 416,04 DA | … | … | … |
You pay the price of the provider that served your request. Prices read 15:48 · speed over the last 30 minutes · uptime over 3 days.
Real requests, real replies. Try any of them yourself — one click, pre-filled.
Two lines to welcome a shop in Oran.
Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.
Try in Chat LabTry your own request — same model, pre-selected.
Open Chat LabSwap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
resp = client.chat.completions.create(
model="relace/relace-apply-3",
messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)
print(resp.choices[0].message.content)Runs this request once on your balance.
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokensstopseedAbout 0,49 DA per message. ↑ 282,91 DA · ↓ 416,04 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Relace Apply 3 merges a suggested code change into your file. You send the instruction, the original code and the edit snippet in that set layout, and it returns the updated file, working through a file of up to about 250 pages. The edit can come from another AI such as GPT-4o or Claude.
Deposit dinars with your Edahabia or CIB card. Every model, Relace Apply 3 included, is paid from that balance. No foreign card, no conversion.
Relace names no languages for Relace Apply 3. Arabic, French and Darja: not stated.
It reads text. Up to 256K tokens in one request, about 250 pages. It writes up to 96 000 words at once.
No. Relace has not published its weights.
Relace. Released 26 September 2025.
Relace Search explores a codebase for you: given a request, it runs between 4 and 12 file-viewing and text-search lookups side by side, then returns the files that matter. It is made to work as a helper that hands its findings to another model, and it keeps about 250 pages in mind at once. Use it to locate code before an edit. It does not write the change, so pair it with a coding model and Relace Apply 3.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first No.
Works through the problem before it answers.
Uses your tools No.
Can call functions your code provides.
Fills your JSON No.
Answers in the JSON shape you give it.
Searches the web No.
Can look things up online while it answers.
Cheaper on repeats No.
A prompt it saw a moment ago costs less the second time.
Open weights No.
Read on docs.relace.ai.
Merge an edit snippet from your coding agent into the full file
Apply the same change across many long files
Turn a partial diff into a complete, updated file