Gemini 2.5 Flash

By Google · released Jun 17, 2025

google/gemini-2.5-flash

Fast and inexpensive, with a very long context. Great for summaries, documents and everyday chat.

Price in TND

The same in the chat and the API. Charged per token, to the millime.

Input	0.990TND/ 1M tokens
Output	8.250TND/ 1M tokens
Cached input	0.248TND/ 1M tokens
Per messageAbout 2,000 tokens in, 600 out	≈ 0.007TND

Prices last updated Oct 20, 2026

Use it from your code

Any OpenAI SDK works. Copy a snippet, add your API key, and send the request.

python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.platform.guitouni-amine.me/v1",
    api_key=os.environ["NOOR_API_KEY"],
)

reply = client.chat.completions.create(
    model="google/gemini-2.5-flash",
    messages=[{"role": "user", "content": "Ahla! Explain recursion in two sentences."}],
)
print(reply.choices[0].message.content)