Hormouz AIHormouzSign in

Google: Gemini 3.6 Flash: AI model

Gemini 3.6 Flash is an efficient Gemini Flash model for coding and app development from Google with a 1M-token context window. Reachable from inside Iran through Hormouz.

Context window:
1,048,576 tokens
Input:
$0.75/1M tokens
Output:
$3.75/1M tokens
Type:
text, image, video, audio
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels: Always thinks · high · medium · low · minimal

Gemini 3.6 Flash is a high-efficiency Google model for coding, agent workflows and web and app development. It aims for polished results with fewer unnecessary edits and less hedging, and it finishes tasks with fewer tokens and fewer model calls. It accepts text, images, video, audio and PDFs over a 1M-token context.

It accepts text, image, file (PDF), audio and video input and returns text, and supports tool calling, structured JSON output and streaming. It always reasons before answering, and you choose how hard it thinks with the reasoning effort setting. Gemini 3.6 Flash is commonly used for web and app development, coding agents, multimodal analysis and efficient general assistants. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs without changes.

Pricing is usage-based: $0.75 per million input tokens and $3.75 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.6-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorGoogle
TypeText, Image, Video, Audio
Context window1,048,576 tokens
Pricing$0.75/M in · $3.75/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

34
Intelligence Index
Better than 66% of models we compared
69.2
Coding Index
Better than 80% of models we compared
29
Agentic Index
Better than 65% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
92.8%
HLE
Humanity's Last Exam
40.8%
AA-LCR
Long-context reasoning
80%
CritPt
Research-level physics reasoning
10.6%
AA Omniscience
Broad factual knowledge accuracy
50%
Non-Hallucination
Rate of avoiding fabricated answers
44.4%

Coding

SciCode
Python for scientific computing
53.4%

Agentic

GDPval
Economically valuable tasks
39.3%

Source: Artificial Analysis

Agentic Game Dev
Top 54%
1,180Elo
Win rate: 47.8%
Android Native
Top 30%
1,217Elo
Win rate: 53.7%
Full-Stack
Top 50%
1,179Elo
Win rate: 44.3%
HTML Slides
Top 74%
1,148Elo
Win rate: 41.9%
Mobile Apps
Top 37%
1,198Elo
Win rate: 50.6%
Python Slides
Top 81%
1,146Elo
Win rate: 38.8%
Web Apps
Top 55%
1,187Elo
Win rate: 45.4%
3D
Top 14%
1,284Elo
Win rate: 53.2%Avg time: 64.6s
ASCII Art
Top 7%
1,289Elo
Win rate: 56.7%Avg time: 60.6s
Code
Top 11%
1,295Elo
Win rate: 53.5%Avg time: 76.5s
Data Viz
Top 8%
1,301Elo
Win rate: 53.3%Avg time: 66.4s
Game Dev
Top 18%
1,275Elo
Win rate: 51.1%Avg time: 78.8s
UI Component
Top 11%
1,305Elo
Win rate: 54.3%Avg time: 65.9s
Website
Top 8%
1,306Elo
Win rate: 55.4%Avg time: 85.3s

Metrics sourced from Design Arena

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.6-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="google/gemini-3.6-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "google/gemini-3.6-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Google: Gemini 3.6 Flash API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Google: Gemini 3.6 Flash and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an accountBuy Gemini API access, paid in rial

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Gemini 3.6 Flash cost?
Pricing is usage-based: $0.75 per million input tokens and $3.75 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use.
How do I access Gemini 3.6 Flash from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Gemini 3.6 Flash compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window and capabilities does Gemini 3.6 Flash have?
It has a 1M-token context window, accepts text, image, file (PDF), audio and video input, and supports tool calling, structured JSON output and streaming. It always reasons before answering, and you choose how hard it thinks with the reasoning effort setting.
What is Gemini 3.6 Flash good for?
Typical uses are web and app development, coding agents, multimodal analysis and efficient general assistants.

Updated 2026-10-13