What is Qwen3.6 Max Preview's context window?

Qwen3.6 Max Preview supports a context window of 256,000 tokens, allowing you to process large documents and maintain long conversations.

How to use Qwen3.6 Max Preview API via Ofox?

Simply set your base URL to https://api.ofox.ai/v1 and use your Ofox API key. The API is OpenAI-compatible — just change the base URL and API key in your existing code.

Qwen3.6 Max Preview

Name: Qwen3.6 Max Preview
Brand: bailian
Price: 2 USD
Availability: InStock
Rating: 5 (1 reviews)

Chat

bailian/qwen3.6-max-preview

CompareGet Started

Qwen3.6-Max-Preview is the largest and most capable model in Alibaba's Qwen3.6 series, currently available as a text-only preview. It builds on Qwen3-Max and Qwen3.6-Plus with further capability improvements. Context: 256K tokens, output: 64K. Available via OpenAI and Anthropic protocols.

Context Window

256K

Max Output Tokens

64K

Released

2026-04-20

Capabilities

Function CallingReasoningPrompt Caching

Available Providers

Aliyun

Supported Protocols

openaianthropic

Providers

Aliyun

Input Tokens

$2.15/M

Output Tokens

$12.86/M

Cache Read

$0.2/M

Cache Write

$1.17/M

$2/M

Web Search

$0.01/R

Protocols

openai/v1/chat/completions

anthropic

Code Examples

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ofox.ai/v1",
    api_key="YOUR_OFOX_API_KEY",
)

response = client.chat.completions.create(
    model="bailian/qwen3.6-max-preview",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)

Benchmarks

LMArena ↗Evaluated as qwen3.6-max-preview

Qwen3.6 Max Preview scores 1460 in the Overall category of the LMArena text leaderboard (style control), ranking #38 of 374 models based on 5,208 human preference votes (updated 2026-07-12).

Benchmark scores for qwen3.6-max-preview on LMArena
Category	Arena Score	95% CI	Rank	Votes
Overall	1460	1452–1469	#38 of 374	5,208
Hard Prompts	1481	1471–1492	#39 of 374	3,406
Coding	1508	1492–1523	#40 of 369	1,550
Math	1477	1447–1507	#23 of 362	359
Creative Writing	1436	1413–1459	#42 of 372	728
Instruction Following	1449	1435–1463	#41 of 374	1,773
Chinese	1497	1464–1530	#42 of 344	315

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology ↗ · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.