Back to models

google/gemini-3.8-flash

llm Tools · Released Oct 07, 2026

Google's fast multimodal model with a 1M-token context.

Context length 1,048,576

Avg latency —

Requests served 9

Success rate 100.0%

Cost per message 8 credits tokens per credit: 500 in / 100 out

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="google/gemini-3.8-flash",
    messages=[{"role": "user", "content": "مرحبا"}],
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://dev.alapi.deep.sa/v1",
  apiKey: "sk-alapi-...",
});

const resp = await client.chat.completions.create({
  model: "google/gemini-3.8-flash",
  messages: [{ role: "user", content: "مرحبا" }],
});

curl https://dev.alapi.deep.sa/v1/chat/completions \
  -H "Authorization: Bearer sk-alapi-..." \
  -H "Content-Type: application/json" \
  -d '{"model": "google/gemini-3.8-flash", "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

Get Started API Docs