Model Library
AlibabaReleased September 23, 2025Qwen3 Max
Alibaba · Released September 23, 2025
Intelligence score
24
At a glance
- Intelligence
- 24
- Speed
- 65.4tokens/sec
- Latency
- 2.50stime to first token
- Input price
- $1.20per 1M tokens
- Output price
- $6.00per 1M tokens
- Context window
- 260Ktokens
- Parameters
- —
Summary
Comparison summary
Qwen3 Max scores 24 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 17). Qwen3 Max generates output at 65.4 tokens per second (based on Alibaba's API), which is above average compared to other non-reasoning models in a similar price tier (median: 61.7 t/s). Qwen3 Max costs $1.20 per 1M input tokens (better than average, median: $1.88) and $6.00 per 1M output tokens (better than average, median: $7.75), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 Max |
|---|---|
| Provider | Alibaba |
| Release date | September 23, 2025 |
| Intelligence score | 24 |
| Speed | 65.4 tokens/sec |
| Latency (TTFT) | 2.50s |
| Input price | $1.20 / 1M tokens |
| Output price | $6.00 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | — |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | No |
| License | — |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-max |
Pricing
Token prices
Price per 1M tokens
Qwen3 Max, as listed in the catalog record
- Input$1.20
- Output$6.00
| Token type | Price per 1M |
|---|---|
| Input | $1.20 |
| Output | $6.00 |
Model Intelligence legacy profile: qwen3-max
FAQ · 18
Frequently asked questions
Qwen3 Max was released on September 23, 2025.
Qwen3 Max was created by Alibaba.
Qwen3 Max scores 24 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 17).
Qwen3 Max generates output at 65.4 tokens per second (based on Alibaba's API), which is above average compared to other non-reasoning models in a similar price tier (median: 61.7 t/s).
Qwen3 Max has a time to first token (TTFT) of 2.50s (based on Alibaba's API), which is somewhat higher than average compared to other non-reasoning models in a similar price tier (median: 1.57s).
Qwen3 Max costs $1.20 per 1M input tokens (better than average, median: $1.88) and $6.00 per 1M output tokens (better than average, median: $7.75), based on Alibaba's API.
Qwen3 Max 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.
No, Qwen3 Max is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 Max supports text input.
Qwen3 Max supports text output.
No, Qwen3 Max does not support image input. It can only process text.
No, Qwen3 Max is not multimodal. It only supports text input.
Qwen3 Max 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 is proprietary. The model weights are not publicly available.
Qwen3 Max is a proprietary model and Alibaba has not disclosed the model size or parameter count.
Qwen3 Max achieves a score of 24 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 Max is available via API through 2 providers.
Qwen3 Max is available through 2 API providers.