Skip to content

Model Library

AlibabaReleased November 3, 2025

Qwen3 Max Thinking (Preview)

Alibaba · Released November 3, 2025

View public research Browse the library

Intelligence score

25

At a glance

Intelligence
25
Speed
59.0tokens/sec
Latency
4.12stime to first token
Input price
$1.20per 1M tokens
Output price
$6.00per 1M tokens
Context window
260Ktokens
Parameters
—

Summary

Comparison summary

Qwen3 Max Thinking (Preview) scores 25 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 28). Qwen3 Max Thinking (Preview) generates output at 59.0 tokens per second (based on Alibaba's API), which is below average compared to other reasoning models in a similar price tier (median: 81.2 t/s). Qwen3 Max Thinking (Preview) costs $1.20 per 1M input tokens (better than average, median: $1.50) and $6.00 per 1M output tokens (better than average, median: $8.40), based on Alibaba's API.

Specifications

Technical specifications

Model nameQwen3 Max Thinking (Preview)
ProviderAlibaba
Release dateNovember 3, 2025
Intelligence score25
Speed59.0 tokens/sec
Latency (TTFT)4.12s
Input price$1.20 / 1M tokens
Output price$6.00 / 1M tokens
Context window260,000 tokens
Parameters—
ReasoningYes
Input modalitiestext
Output modalities—
Open weightsNo
License—
API availability—
SourceModel Intelligence legacy profile: qwen3-max-thinking-preview

Pricing

Token prices

Price per 1M tokens

Qwen3 Max Thinking (Preview), as listed in the catalog record

Input $1.20 and output $6.00 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$1.20
  2. Output$6.00

Model Intelligence legacy profile: qwen3-max-thinking-preview

FAQ · 18

Frequently asked questions

Qwen3 Max Thinking (Preview) was released on November 3, 2025.

Qwen3 Max Thinking (Preview) was created by Alibaba.

Qwen3 Max Thinking (Preview) scores 25 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 28).

Qwen3 Max Thinking (Preview) generates output at 59.0 tokens per second (based on Alibaba's API), which is below average compared to other reasoning models in a similar price tier (median: 81.2 t/s).

Qwen3 Max Thinking (Preview) has a time to first token (TTFT) of 4.12s (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 Max Thinking (Preview) costs $1.20 per 1M input tokens (better than average, median: $1.50) and $6.00 per 1M output tokens (better than average, median: $8.40), based on Alibaba's API.

Qwen3 Max Thinking (Preview) costs $1.20 per 1M input tokens and $6.00 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.68 per 1M tokens. Pricing may vary by provider.

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

Qwen3 Max Thinking (Preview) supports text input.

Qwen3 Max Thinking (Preview) supports text output.

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

No, Qwen3 Max Thinking (Preview) is not multimodal. It only supports text input.

Qwen3 Max Thinking (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 Max Thinking (Preview) is proprietary. The model weights are not publicly available.

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

Qwen3 Max Thinking (Preview) achieves a score of 25 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Qwen3 Max Thinking (Preview) is available via API through 1 provider.

Qwen3 Max Thinking (Preview) is available through 1 API provider.