uttapen
Create an API key

Qwen2.5 72B Instruct API: toman pricing and code

qwen/qwen-2.5-72b-instruct

toolsjson
Create a keyTry it
Input · per 1M tokens
104,445 toman
Output · per 1M tokens
116,050 toman
One 1,000-word request ≈
287 toman

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

Qwen2.5 72B Instruct example: JSON output against a schema

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

from openai import OpenAI
import json

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

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="qwen/qwen-2.5-72b-instruct",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))

What is Qwen2.5 72B Instruct good for?

Qwen (Alibaba) publishes this model; we expose it under the id "qwen/qwen-2.5-72b-instruct". Its context window is 32,768 tokens, roughly 25k English words in one request. A single response can run to 16,384 tokens. On price it sits in the "very cheap" band — cheaper than 71 and dearer than 335 of the other paid models in the catalogue.

What it can do beyond plain text: it supports tool calling, so it can invoke your own functions with valid arguments; it returns schema-valid JSON through response_format, ready to hand to your code. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper.

Pricing is 104,445 toman per 1M input tokens and 116,050 per 1M output tokens. A 1,000-word round trip on Qwen2.5 72B Instruct lands near 287 toman. 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 DeepSeek V3.2: Qwen2.5 72B Instruct works out roughly 1.1× more expensive, and its context window is smaller. 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 348 thousand-word requests on Qwen2.5 72B Instruct, and every 1,000 toman is about 3,484 words of round trip. A job with one million input tokens and one million output tokens comes to 220,495 toman in total. Filling this model's 32,768-token window costs 3,422 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "qwen/qwen-2.5-7b-instruct", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 2.5× dearer (287 against 113 toman). Maximum answer length differs as well: 16,384 against 29,491 tokens. On parameters, this one takes logit_bias.

Qwen (Alibaba) has 53 models in our catalogue; the cheapest is Qwen3.7 Flash at 60 toman per thousand words and the dearest Qwen3.8 Max (0902) at 3,017. Among the less common parameters it accepts logit_bias, min_p, repetition_penalty, top_k — all through the standard request body. It does not support include_reasoning, reasoning, 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 Aion-RP 1.0 (8B) at 32,768 tokens.

Good fits: high-volume work such as classification, tagging and bulk summarising, agents that reach out to APIs and databases, extracting data against a fixed schema.

Provider's own description

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

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 out203 toman
Summarising a ten-page document4,000 in + 600 out487 toman
Classifying a thousand short rows120,000 in + 20,000 out14,854 toman

Frequently asked

How do I call Qwen2.5 72B Instruct 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 "qwen/qwen-2.5-72b-instruct". Nothing else in your code changes.
What does Qwen2.5 72B Instruct cost in toman?
104,445 toman per 1M input tokens and 116,050 toman per 1M output tokens; a 1,000-word request is around 287 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Qwen2.5 72B Instruct take?
Up to 32,768 tokens per request, roughly 25k words. A single answer can reach 16,384 tokens.
Does Qwen2.5 72B Instruct support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Structured output through response_format works too.