Model Library
AlibabaReleased February 24, 2026Qwen3.5 27B
Alibaba · Released February 24, 2026
Intelligence score
34
At a glance
- Intelligence
- 34
- Speed
- 85.4tokens/sec
- Latency
- 5.78stime to first token
- Input price
- $0.30per 1M tokens
- Output price
- $2.40per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 27.8billions
Summary
Comparison summary
Qwen3.5 27B (Reasoning) scores 34 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). Qwen3.5 27B (Reasoning) generates output at 85.4 tokens per second (based on Alibaba's API), which is below average compared to other open weight models of similar size (median: 101.0 t/s). Qwen3.5 27B (Reasoning) costs $0.30 per 1M input tokens (at the higher end, median: $0.18) and $2.40 per 1M output tokens (at the higher end, median: $0.40), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3.5 27B |
|---|---|
| Provider | Alibaba |
| Release date | February 24, 2026 |
| Intelligence score | 34 |
| Speed | 85.4 tokens/sec |
| Latency (TTFT) | 5.78s |
| Input price | $0.30 / 1M tokens |
| Output price | $2.40 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 27.8B |
| Reasoning | Yes |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-5-27b |
Pricing
Token prices
Price per 1M tokens
Qwen3.5 27B, as listed in the catalog record
- Input$0.30
- Output$2.40
| Token type | Price per 1M |
|---|---|
| Input | $0.30 |
| Output | $2.40 |
Model Intelligence legacy profile: qwen3-5-27b
FAQ · 19
Frequently asked questions
Qwen3.5 27B (Reasoning) was released on February 24, 2026.
Qwen3.5 27B (Reasoning) was created by Alibaba.
Qwen3.5 27B (Reasoning) scores 34 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Qwen3.5 27B (Reasoning) generates output at 85.4 tokens per second (based on Alibaba's API), which is below average compared to other open weight models of similar size (median: 101.0 t/s).
Qwen3.5 27B (Reasoning) has a time to first token (TTFT) of 5.78s (based on Alibaba's API), which is at the higher end compared to other open weight models of similar size (median: 2.09s).
Qwen3.5 27B (Reasoning) costs $0.30 per 1M input tokens (at the higher end, median: $0.18) and $2.40 per 1M output tokens (at the higher end, median: $0.40), based on Alibaba's API.
Qwen3.5 27B (Reasoning) costs $0.30 per 1M input tokens and $2.40 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.51 per 1M tokens. Pricing may vary by provider.
Yes, Qwen3.5 27B (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 27B (Reasoning) supports text and image input.
Qwen3.5 27B (Reasoning) supports text output.
Yes, Qwen3.5 27B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Qwen3.5 27B (Reasoning) is multimodal. It can process text and image input and generate text output.
Qwen3.5 27B (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 27B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3.5 27B (Reasoning) has 27.8 billion parameters.
Qwen3.5 27B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3.5 27B (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 27B (Reasoning) is available via API through 6 providers.
Qwen3.5 27B (Reasoning) is available through 6 API providers.