Model Library
AlibabaReleased February 16, 2026Qwen3.5 397B A17B
Alibaba · Released February 16, 2026
Intelligence score
34
At a glance
- Intelligence
- 34
- Speed
- 51.4tokens/sec
- Latency
- 2.83stime to first token
- Input price
- $0.60per 1M tokens
- Output price
- $3.60per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 397billions
Summary
Comparison summary
Qwen3.5 397B A17B (Reasoning) scores 34 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 25). Qwen3.5 397B A17B (Reasoning) generates output at 51.4 tokens per second (based on Alibaba's API), which is at the lower end compared to other open weight models of similar size (median: 61.7 t/s). Qwen3.5 397B A17B (Reasoning) costs $0.60 per 1M input tokens (somewhat higher than average, median: $0.59) and $3.60 per 1M output tokens (at the higher end, median: $2.20), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3.5 397B A17B |
|---|---|
| Provider | Alibaba |
| Release date | February 16, 2026 |
| Intelligence score | 34 |
| Speed | 51.4 tokens/sec |
| Latency (TTFT) | 2.83s |
| Input price | $0.60 / 1M tokens |
| Output price | $3.60 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 397B |
| Reasoning | Yes |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-5-397b-a17b |
Pricing
Token prices
Price per 1M tokens
Qwen3.5 397B A17B, as listed in the catalog record
- Input$0.60
- Output$3.60
| Token type | Price per 1M |
|---|---|
| Input | $0.60 |
| Output | $3.60 |
Model Intelligence legacy profile: qwen3-5-397b-a17b
FAQ · 21
Frequently asked questions
Qwen3.5 397B A17B (Reasoning) was released on February 16, 2026.
Qwen3.5 397B A17B (Reasoning) was created by Alibaba.
Qwen3.5 397B A17B (Reasoning) scores 34 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 25).
Qwen3.5 397B A17B (Reasoning) generates output at 51.4 tokens per second (based on Alibaba's API), which is at the lower end compared to other open weight models of similar size (median: 61.7 t/s).
Qwen3.5 397B A17B (Reasoning) has a time to first token (TTFT) of 2.83s (based on Alibaba's API), which is at the higher end compared to other open weight models of similar size (median: 2.01s).
Qwen3.5 397B A17B (Reasoning) costs $0.60 per 1M input tokens (somewhat higher than average, median: $0.59) and $3.60 per 1M output tokens (at the higher end, median: $2.20), based on Alibaba's API.
Qwen3.5 397B A17B (Reasoning) costs $0.60 per 1M input tokens and $3.60 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.90 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Qwen3.5 397B A17B (Reasoning) generated 88M output tokens, which is better than average compared to other open weight models of similar size (median: 92M).
Yes, Qwen3.5 397B A17B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Qwen3.5 397B A17B (Reasoning) supports text and image input.
Qwen3.5 397B A17B (Reasoning) supports text output.
Yes, Qwen3.5 397B A17B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Qwen3.5 397B A17B (Reasoning) is multimodal. It can process text and image input and generate text output.
Qwen3.5 397B A17B (Reasoning) has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3.5 397B A17B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3.5 397B A17B (Reasoning) has 397 billion parameters (17 billion active).
Qwen3.5 397B A17B (Reasoning) is a Mixture of Experts (MoE) model with 397 billion total parameters, but only 17 billion active parameters are used during inference.
Qwen3.5 397B A17B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3.5 397B A17B (Reasoning) achieves a score of 34 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3.5 397B A17B (Reasoning) is available via API through 11 providers.
Qwen3.5 397B A17B (Reasoning) is available through 11 API providers.