Model Library
AlibabaReleased March 2, 2026Qwen3.5 9B
Alibaba · Released March 2, 2026
Intelligence score
21
At a glance
- Intelligence
- 21
- Speed
- 59.4tokens/sec
- Latency
- 1.71stime to first token
- Input price
- $0.10per 1M tokens
- Output price
- $0.15per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 9.65billions
Summary
Comparison summary
Qwen3.5 9B (Reasoning) scores 21 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). Qwen3.5 9B (Reasoning) generates output at 59.4 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight models of similar size (median: 101.0 t/s). Qwen3.5 9B (Reasoning) costs $0.10 per 1M input tokens (better than average, median: $0.18) and $0.15 per 1M output tokens (very competitive, median: $0.40), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Qwen3.5 9B |
|---|---|
| Provider | Alibaba |
| Release date | March 2, 2026 |
| Intelligence score | 21 |
| Speed | 59.4 tokens/sec |
| Latency (TTFT) | 1.71s |
| Input price | $0.10 / 1M tokens |
| Output price | $0.15 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 9.65B |
| Reasoning | Yes |
| Input modalities | text, image, video |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-5-9b |
Pricing
Token prices
Price per 1M tokens
Qwen3.5 9B, as listed in the catalog record
- Input$0.10
- Output$0.15
| Token type | Price per 1M |
|---|---|
| Input | $0.10 |
| Output | $0.15 |
Model Intelligence legacy profile: qwen3-5-9b
FAQ · 20
Frequently asked questions
Qwen3.5 9B (Reasoning) was released on March 2, 2026.
Qwen3.5 9B (Reasoning) was created by Alibaba.
Qwen3.5 9B (Reasoning) scores 21 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Qwen3.5 9B (Reasoning) generates output at 59.4 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight models of similar size (median: 101.0 t/s).
Qwen3.5 9B (Reasoning) has a time to first token (TTFT) of 1.71s (based on the median across providers serving the model), which is better than average compared to other open weight models of similar size (median: 2.09s).
Qwen3.5 9B (Reasoning) costs $0.10 per 1M input tokens (better than average, median: $0.18) and $0.15 per 1M output tokens (very competitive, median: $0.40), based on the median across providers serving the model.
Qwen3.5 9B (Reasoning) costs $0.10 per 1M input tokens and $0.15 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.11 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Qwen3.5 9B (Reasoning) generated 210M output tokens, which is at the higher end compared to other open weight models of similar size (median: 32M).
Yes, Qwen3.5 9B (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 9B (Reasoning) supports text, image, and video input.
Qwen3.5 9B (Reasoning) supports text output.
Yes, Qwen3.5 9B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Qwen3.5 9B (Reasoning) is multimodal. It can process text, image, and video input and generate text output.
Qwen3.5 9B (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 9B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3.5 9B (Reasoning) has 9.65 billion parameters.
Qwen3.5 9B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3.5 9B (Reasoning) achieves a score of 21 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3.5 9B (Reasoning) is available via API through 2 providers.
Qwen3.5 9B (Reasoning) is available through 2 API providers.