Model Library
AlibabaReleased April 16, 2026Qwen3.6 35B A3B
Alibaba · Released April 16, 2026
Intelligence score
32
At a glance
- Intelligence
- 32
- Speed
- 165.6tokens/sec
- Latency
- 2.45stime to first token
- Input price
- $0.25per 1M tokens
- Output price
- $1.49per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 36billions
Summary
Comparison summary
Qwen3.6 35B A3B (Reasoning) scores 32 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). Qwen3.6 35B A3B (Reasoning) generates output at 165.6 tokens per second (based on Alibaba's API), which is well above average compared to other open weight models of similar size (median: 101.0 t/s). Qwen3.6 35B A3B (Reasoning) costs $0.25 per 1M input tokens (somewhat higher than average, median: $0.18) and $1.49 per 1M output tokens (somewhat higher than average, median: $0.40), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3.6 35B A3B |
|---|---|
| Provider | Alibaba |
| Release date | April 16, 2026 |
| Intelligence score | 32 |
| Speed | 165.6 tokens/sec |
| Latency (TTFT) | 2.45s |
| Input price | $0.25 / 1M tokens |
| Output price | $1.49 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 36B |
| Reasoning | Yes |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-6-35b-a3b |
Pricing
Token prices
Price per 1M tokens
Qwen3.6 35B A3B, as listed in the catalog record
- Input$0.25
- Output$1.49
| Token type | Price per 1M |
|---|---|
| Input | $0.25 |
| Output | $1.49 |
Model Intelligence legacy profile: qwen3-6-35b-a3b
FAQ · 21
Frequently asked questions
Qwen3.6 35B A3B (Reasoning) was released on April 16, 2026.
Qwen3.6 35B A3B (Reasoning) was created by Alibaba.
Qwen3.6 35B A3B (Reasoning) scores 32 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Qwen3.6 35B A3B (Reasoning) generates output at 165.6 tokens per second (based on Alibaba's API), which is well above average compared to other open weight models of similar size (median: 101.0 t/s).
Qwen3.6 35B A3B (Reasoning) has a time to first token (TTFT) of 2.45s (based on Alibaba's API), which is somewhat higher than average compared to other open weight models of similar size (median: 2.09s).
Qwen3.6 35B A3B (Reasoning) costs $0.25 per 1M input tokens (somewhat higher than average, median: $0.18) and $1.49 per 1M output tokens (somewhat higher than average, median: $0.40), based on Alibaba's API.
Qwen3.6 35B A3B (Reasoning) costs $0.25 per 1M input tokens and $1.49 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.37 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Qwen3.6 35B A3B (Reasoning) generated 150M output tokens, which is at the higher end compared to other open weight models of similar size (median: 32M).
Yes, Qwen3.6 35B A3B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Qwen3.6 35B A3B (Reasoning) supports text and image input.
Qwen3.6 35B A3B (Reasoning) supports text output.
Yes, Qwen3.6 35B A3B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Qwen3.6 35B A3B (Reasoning) is multimodal. It can process text and image input and generate text output.
Qwen3.6 35B A3B (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, Qwen3.6 35B A3B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3.6 35B A3B (Reasoning) has 36 billion parameters (3 billion active).
Qwen3.6 35B A3B (Reasoning) is a Mixture of Experts (MoE) model with 36 billion total parameters, but only 3 billion active parameters are used during inference.
Qwen3.6 35B A3B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3.6 35B A3B (Reasoning) achieves a score of 32 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3.6 35B A3B (Reasoning) is available via API through 9 providers.
Qwen3.6 35B A3B (Reasoning) is available through 9 API providers.