Back to models

gpt-oss-20b

Saudi-hosted
llm Tools · Released Dec 04, 2025
Context length —
Avg latency ~568ms
Requests served 913
Success rate 98.1%
Cost per message 1 request

Request volume — last 30 days

−100% vs last week
Oct 5 — 1 Oct 6 — 2 Oct 5 Oct 6

Quick start

from openai import OpenAI

client = OpenAI(
    base_url="https://dev.alapi.deep.sa/v1",
    api_key="sk-alapi-...",
)

resp = client.chat.completions.create(
    model="gpt-oss-20b",
    messages=[{"role": "user", "content": "مرحبا"}],
)

Saudi-hosted models and our tools cost 1 request per call, whatever the size. Global models use credits View full pricing details

Activate account?

Activate this account?