Hormouz AIHormouzSign in

Qwen: Qwen3.6 Plus: AI model

Qwen3.6 Plus is a Qwen multimodal vision-language model with a built-in thinking mode for deep reasoning, with a 1M-token context window. Reachable from inside Iran through Hormouz.

Context window:
1,000,000 tokens
Input:
$0.33/1M tokens
Output:
$1.95/1M tokens
Type:
text, image, video
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels:

Qwen3.6 Plus is a vision-language model from Alibaba's Qwen series, with a context window of up to 1M tokens; it is strong at understanding text, images and video, tool calling. It has a built-in thinking mode that produces explicit step-by-step reasoning before the final answer.

Through Hormouz the model is served behind an OpenAI-compatible API. Point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged. Pricing is usage-based: $0.325 per million input tokens and $1.95 per million output tokens.

Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.6-plus",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorQwen
TypeText, Image, Video
Context window1,000,000 tokens
Pricing$0.33/M in · $1.95/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

54.5
Coding Index
Better than 61% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
88.2%
HLE
Humanity's Last Exam
27.8%
IFBench
Instruction-following
75.2%
AA-LCR
Long-context reasoning
78.3%
CritPt
Research-level physics reasoning
2.9%
AA Omniscience
Broad factual knowledge accuracy
26.4%
Non-Hallucination
Rate of avoiding fabricated answers
65.4%

Coding

Terminal-Bench Hard
Agentic coding & terminal use
43.9%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
97.7%
GDPval
Economically valuable tasks
24.7%

Source: Artificial Analysis

Design Arena

How Design Arena works ↗
3D
Top 33%
1,213Elo
Win rate: 50.8%Avg time: 173s
ASCII Art
Top 76%
1,126Elo
Win rate: 41.9%Avg time: 147s
Code
Top 28%
1,241Elo
Win rate: 50.5%Avg time: 271s
Data Viz
Top 29%
1,237Elo
Win rate: 51%Avg time: 233s
Game Dev
Top 29%
1,224Elo
Win rate: 49.1%Avg time: 270s
SVG
Top 40%
1,161Elo
Win rate: 50.7%Avg time: 142s
UI Component
Top 31%
1,238Elo
Win rate: 50.8%Avg time: 252s
Website
Top 27%
1,248Elo
Win rate: 50.4%Avg time: 322s

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": "qwen/qwen3.6-plus",
    "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="qwen/qwen3.6-plus",
    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: "qwen/qwen3.6-plus",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Qwen: Qwen3.6 Plus API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Qwen: Qwen3.6 Plus 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 account

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

What is Qwen3.6 Plus and what is it good for?
Qwen3.6 Plus is a Qwen vision-language model. It handles both text and visual inputs for tasks like document parsing, visual Q&A and OCR.
What is the context window of Qwen3.6 Plus?
The model supports up to 1M tokens of context, which suits long documents and multi-turn conversations.
How much does Qwen3.6 Plus cost?
Pricing is usage-based: $0.325 per million input tokens and $1.95 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Qwen3.6 Plus 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 required.
Is Qwen3.6 Plus compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
Does Qwen3.6 Plus support a thinking / reasoning mode?
Yes. It produces explicit step-by-step reasoning before its final answer, which helps on math, coding and multi-step logic tasks.

Updated 2026-10-13