فا

Qwen: Qwen3.6 Max Preview

by Qwen

qwen/qwen3.6-max-preview
Healthy

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...

Context

262Ktokens

About 374 pages of text at once

Max output

66Ktokens

About 94 pages in one answer

Intelligence

28.4/ 100

Above 47% of the catalogue

Output speed

—

Not measured yet

First token

—

Not measured yet

Health, 30 days

81.38%

9 of 30 days without a fault

IranRouter’s measurements

Price & cost

Every rate in Rial. A request pays only for the tokens it actually uses.

Input2,813,967IRR / 1M tokens
Output16,883,803IRR / 1M tokens
Reasoning tokensThe output rate16,883,803IRR / 1M tokens
Cache write, 5 minutes3,517,459IRR / 1M tokens

Under these conditions, these rates replace the ones above:

Prompts over 128K tokens

Input4,329,180IRR / 1M tokens
Output25,975,082IRR / 1M tokens
Cache write, 5 minutes5,411,475IRR / 1M tokens

What would this model cost you a month?

Monthly cost

557.17MIRR

18.57M IRR a day, 9,286 IRR each request

The same work on peer models

Qwen: Qwen3.6 Max Preview557.17MIRRThis model
Z.ai: GLM 5.3 Flash11.3MIRR98% cheaperGoogle: Gemini 3.8 Flash369.36MIRR34% cheaperZ.ai: GLM 5.386.16MIRR85% cheaper

30 days at today’s rate.

Rial price over 90 days

It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.

InputOutput

Performance, 30 days

Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.

Daily health81.38%

Time to first token1.26 s

Output speed62 tokens/s

Place in the market

By usage across the global model market.

This model isn’t ranked yet.

Among its peers

Cost of one message against intelligence; this model is highlighted.

Cost of one message, IRR (log scale)

Capabilities

Image inputNo
Audio inputNo
Tool callingYes
JSON outputYes
ReasoningYes
Web searchNo
Prompt cacheNo
Makes imagesNo
Open weightsNo
On the free planNo
Input
Text
Output
Text

Parameters it accepts

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Other benchmarks

Intelligence index28

Start in a minute

The official OpenAI and Anthropic SDKs; only the address and the key change.

Base URLhttps://iranrouter.com/v1
Model IDqwen/qwen3.6-max-preview
API keyCreate one in the dashboard
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://iranrouter.com/v1",
    api_key="ir-...",
)

r = client.chat.completions.create(
    model="qwen/qwen3.6-max-preview",
    messages=[{"role": "user", "content": "Hello, introduce yourself"}],
)
print(r.choices[0].message.content)
The full guide in the docs: keys, streaming and errors

Peer models

Its family and models with a close score; the last column compares one message’s cost with this model.

ModelAgainst this model
Z.ai: GLM 5.3 FlashZ.ai29227.8771M98% cheaper
Google: Gemini 3.8 FlashGoogle9,23430.5741M34% cheaper
Z.ai: GLM 5.3Z.ai2,29831.7821M84% cheaper
DeepSeek: DeepSeek V4 Pro 0813DeepSeek11,51023.1521M18% cheaper
SpaceXAI: Grok 4.7xAI19,1523571500K36% dearer
Z.ai: GLM 5.3 Flash292 IRRZ.ai98% cheaperGoogle: Gemini 3.8 Flash9,234 IRRGoogle34% cheaperZ.ai: GLM 5.32,298 IRRZ.ai84% cheaperDeepSeek: DeepSeek V4 Pro 081312K IRRDeepSeek18% cheaperSpaceXAI: Grok 4.719K IRRxAI36% dearer

Technical specs

ID
qwen/qwen3.6-max-preview
Maker
Qwen
Tokenizer
Qwen
Released
Apr 27, 2026
Added to IranRouter
Aug 19, 2026
Context
262,144 tokens
Max output
65,536 tokens

Scores by Artificial Analysis

Qwen: Qwen3.6 Max PreviewOne message about 14,070 IRRStart with this model