Skip to content

Model Library

AlibabaReleased April 20, 2026

Qwen3.6 Max Preview

Alibaba · Released April 20, 2026

View public research Browse the library

Intelligence score

40

At a glance

Intelligence
40
Speed
45.1tokens/sec
Latency
3.38stime to first token
Input price
$1.30per 1M tokens
Output price
$7.80per 1M tokens
Context window
260Ktokens
Parameters
—

Summary

Comparison summary

Qwen3.6 Max Preview scores 40 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 28). Qwen3.6 Max Preview generates output at 45.1 tokens per second (based on Alibaba's API), which is at the lower end compared to other reasoning models in a similar price tier (median: 81.2 t/s). Qwen3.6 Max Preview costs $1.30 per 1M input tokens (better than average, median: $1.50) and $7.80 per 1M output tokens (better than average, median: $8.40), based on Alibaba's API.

Specifications

Technical specifications

Model nameQwen3.6 Max Preview
ProviderAlibaba
Release dateApril 20, 2026
Intelligence score40
Speed45.1 tokens/sec
Latency (TTFT)3.38s
Input price$1.30 / 1M tokens
Output price$7.80 / 1M tokens
Context window260,000 tokens
Parameters—
ReasoningYes
Input modalitiestext
Output modalities—
Open weightsNo
License—
API availability—
SourceModel Intelligence legacy profile: qwen3-6-max

Pricing

Token prices

Price per 1M tokens

Qwen3.6 Max Preview, as listed in the catalog record

Input $1.30 and output $7.80 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$1.30
  2. Output$7.80

Model Intelligence legacy profile: qwen3-6-max

FAQ · 18

Frequently asked questions

Qwen3.6 Max Preview was released on April 20, 2026.

Qwen3.6 Max Preview was created by Alibaba.

Qwen3.6 Max Preview scores 40 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 28).

Qwen3.6 Max Preview generates output at 45.1 tokens per second (based on Alibaba's API), which is at the lower end compared to other reasoning models in a similar price tier (median: 81.2 t/s).

Qwen3.6 Max Preview has a time to first token (TTFT) of 3.38s (based on Alibaba's API), which is somewhat higher than average compared to other reasoning models in a similar price tier (median: 2.78s).

Qwen3.6 Max Preview costs $1.30 per 1M input tokens (better than average, median: $1.50) and $7.80 per 1M output tokens (better than average, median: $8.40), based on Alibaba's API.

Qwen3.6 Max Preview costs $1.30 per 1M input tokens and $7.80 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.13 per 1M tokens. Pricing may vary by provider.

Yes, Qwen3.6 Max Preview is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

Qwen3.6 Max Preview supports text input.

Qwen3.6 Max Preview supports text output.

No, Qwen3.6 Max Preview does not support image input. It can only process text.

No, Qwen3.6 Max Preview is not multimodal. It only supports text input.

Qwen3.6 Max Preview has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.

No, Qwen3.6 Max Preview is proprietary. The model weights are not publicly available.

Qwen3.6 Max Preview is a proprietary model and Alibaba has not disclosed the model size or parameter count.

Qwen3.6 Max Preview achieves a score of 40 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Qwen3.6 Max Preview is available via API through 1 provider.

Qwen3.6 Max Preview is available through 1 API provider.