qwen2.5-72b-instruct

Live
Alibaba

Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilingual capabilities for over 29 languages.

Modality

Chat

Context window

33K tokens

Max output

16K tokens

Region

US

Published

Jul 21, 2026

Pricing

Input

20.23

EGP per 1M tokens

Output

22.48

EGP per 1M tokens

Use it via the API

qwen2.5-72b-instruct works with any OpenAI-compatible SDK — point the base URL at https://preprod-backend.sovereigneg.com/v1 and use your SovereignEG API key.

Run inference

OpenAI-compatible — POST /v1/chat/completions — drop-in for any OpenAI SDK.

from openai import OpenAI

client = OpenAI(
    base_url="https://preprod-backend.sovereigneg.com/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="qwen2.5-72b-instruct",
    messages=[
        {"role": "user", "content": "What are some fun things to do in Cairo?"}
    ],
)

print(response.choices[0].message.content)

Frequently asked questions

How much does qwen2.5-72b-instruct cost?

20.23 EGP per 1M input tokens; 22.48 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.

What is the context window of qwen2.5-72b-instruct?

qwen2.5-72b-instruct supports a context window of 32,768 tokens (33K), with up to 16,384 output tokens per response.

Where is qwen2.5-72b-instruct hosted?

qwen2.5-72b-instruct is served from US (US-hosted inference).

How do I use qwen2.5-72b-instruct via the API?

qwen2.5-72b-instruct is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://preprod-backend.sovereigneg.com/v1 and call /v1/chat/completions with model "qwen2.5-72b-instruct" and your API key.