GeekRadar / The comparison desk

COMPARE.

AI models

alibaba

Qwen 3.6 Max (Preview)

AI model Released Apr 20, 2026

Context window: 262,144 tokens^*
Maximum output: 65,536 tokens^*
Open weights: No^*

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Qwen 3.6 Max (Preview) 149.8^* Qwen 3.6 Max (Preview) · 95% interval 147.9–151.9

Run it locally

Inference · memory estimate

Qwen 3.6 Max (Preview)

Closed weights. No supported local deployment or GPU requirement is published.

Capabilities

Context window: 262,144 tokens^*
Maximum output: 65,536 tokens^*
Reasoning: Yes^*
Tool calling: Yes^*
Open weights: No^*
Knowledge cutoff: 2025-04^*

Input modalities

text^*

Output modalities

text^*

System configuration

Detailed specifications

Specifications 1 · 2 fields

Organization: Alibaba^*
Organization country: China^*

Specifications 2 · 16 fields

File attachments

No^*

Context window

262,144^* tokens

Model family

qwen^*

Input modalities

text^*

Knowledge cutoff

2025-04^*

Open weights

No^*

Maximum output

65,536^* tokens

Output modalities

text^*

API service · Merge Gateway · qwen/qwen3.6-max-preview

Provider

Merge Gateway^*

Model

qwen/qwen3.6-max-preview^*

Snapshot

2026-10-26^*

Token limits

context: 256,000^*
output: 65,536^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Knowledge cutoff

2025-04^*

Prices (USD per million tokens)

input: 1.31^*
output: 7.88^*

API service · Ofox · qwen/qwen3.6-max-preview

Provider

Ofox^*

Model

qwen/qwen3.6-max-preview^*

Snapshot

2026-10-26^*

Token limits

context: 256,000^*
output: 64,000^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
budget_tokens^*

Tool calling

Yes^*

Temperature control

Yes^*

File attachments

No^*

Knowledge cutoff

2025-04^*

Prices (USD per million tokens)

input: 2.15^*
output: 12.86^*
cache_read: 0.2^*
cache_write: 1.17^*

API service · AIHubMix · qwen3.6-max-preview

Provider

AIHubMix^*

Model

qwen3.6-max-preview^*

Snapshot

2026-10-26^*

Token limits

context: 240,000^*
output: 64,000^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Availability status

deprecated^*

Interleaved reasoning

field: reasoning_content^*

Knowledge cutoff

2025-04^*

Prices (USD per million tokens)

input

1.27^*

output

7.61^*

cache_read

0.1268^*

cache_write

1.585^*

tiers

input
2.11^*
output
12.67^*
cache_read
0.2112^*
cache_write
2.64^*
tier
type
context^*
size
128,000^*

API service · NanoGPT · qwen/qwen3.6-max-preview

Provider

NanoGPT^*

Model

qwen/qwen3.6-max-preview^*

Snapshot

2026-10-26^*

Token limits

context: 245,760^*
input: 245,760^*
output: 65,536^*

Modalities

input: text^*
output: text^*

Reasoning

No^*

Tool calling

No^*

Structured output

No^*

Temperature control

Yes^*

File attachments

No^*

Knowledge cutoff

2025-04^*

Prices (USD per million tokens)

input: 1.04^*
output: 6.24^*
cache_read: 0.52^*

API service · Ofox · bailian/qwen3.6-max-preview

Provider

Ofox^*

Model

bailian/qwen3.6-max-preview^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 65,536^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
budget_tokens^*

Tool calling

Yes^*

Temperature control

Yes^*

File attachments

No^*

Knowledge cutoff

2025-04^*

Prices (USD per million tokens)

input: 2.15^*
output: 12.86^*
cache_read: 0.2^*
cache_write: 1.17^*

Reasoning

Yes^*

Temperature control

Yes^*

Tool calling

Yes^*

* Provisional data