Create an API key

Relace Apply 3 API: toman pricing and code

relace/relace-apply-3

Create a keyTry it
Input · per 1M tokens
294,286 toman
Output · per 1M tokens
432,774 toman
One 1,000-word request ≈
945 toman

You are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups

Relace Apply 3 example: rewriting tone

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

stream = client.chat.completions.create(
    model="relace/relace-apply-3",
    messages=[{"role": "user", "content": "Rewrite this support reply politely: \"That's your problem, just try again.\""}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });

const stream = await client.chat.completions.create({
  model: "relace/relace-apply-3",
  messages: [{ role: "user", content: "Rewrite this support reply politely: \"That's your problem, just try again.\"" }],
  stream: true,
});
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "relace/relace-apply-3",
    "messages": [{"role": "user", "content": "Rewrite this support reply politely: \"That's your problem, just try again.\""}],
    "stream": true
  }'

What is Relace Apply 3 good for?

Relace publishes this model; we expose it under the id "relace/relace-apply-3". Its context window is 256,000 tokens, roughly 192k English words in one request. A single response can run to 128,000 tokens. On price it sits in the "cheap" band — cheaper than 227 and dearer than 167 of the other paid models in the catalogue.

This one handles text only. If you need function calling or image understanding, pick another model from the same catalogue — swapping is a one-line change.

For a back-of-envelope figure: about 945 toman per 1,000-word exchange (294,286 in, 432,774 out, per 1M tokens). You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is MiniMax M2-her: Relace Apply 3 works out about 40% more expensive, and its context window is larger. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 106 thousand-word requests on Relace Apply 3, and every 1,000 toman is about 1,058 words of round trip. A job with one million input tokens and one million output tokens comes to 727,061 toman in total. Filling this model's 256,000-token window costs 75,337 toman on the input side alone, which is the real reason to keep conversation history short.

Relace has 2 models in our catalogue; the cheapest is Relace Apply 3 at 945 toman per thousand words and the dearest Relace Search at 1,800. It does not support include_reasoning, reasoning, response_format, temperature, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Command A at 256,000 tokens.

What to use it for: high-volume work such as classification, tagging and bulk summarising, analysing a long document or codebase in one request.

Provider's own description

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out615 toman
Summarising a ten-page document4,000 in + 600 out1,437 toman
Classifying a thousand short rows120,000 in + 20,000 out43,970 toman

Frequently asked

How do I call Relace Apply 3 from Iran?
Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "relace/relace-apply-3". Nothing else in your code changes.
What does Relace Apply 3 cost in toman?
294,286 toman per 1M input tokens and 432,774 toman per 1M output tokens; a 1,000-word request is around 945 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Relace Apply 3 take?
Up to 256,000 tokens per request, roughly 192k words. A single answer can reach 128,000 tokens.
Can I stream Relace Apply 3's output?
Yes — with stream=true you get SSE events as the tokens are produced. This model has no tool calling and no image input, so pick a different one if you need either.