Model Library
AlibabaReleased April 16, 2026Qwen3.6 35B A3B
Alibaba · Released April 16, 2026
Intelligence score
24
At a glance
- Intelligence
- 24
- Speed
- 179.9tokens/sec
- Latency
- 2.41stime to first token
- Input price
- $0.38per 1M tokens
- Output price
- $2.25per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 36billions
Summary
Comparison summary
Qwen3.6 35B A3B (Non-reasoning) scores 24 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 6). Qwen3.6 35B A3B (Non-reasoning) generates output at 179.9 tokens per second (based on Alibaba's API), which is well above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Qwen3.6 35B A3B (Non-reasoning) costs $0.38 per 1M input tokens (at the higher end, median: $0.15) and $2.25 per 1M output tokens (at the higher end, median: $0.32), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3.6 35B A3B |
|---|---|
| Provider | Alibaba |
| Release date | April 16, 2026 |
| Intelligence score | 24 |
| Speed | 179.9 tokens/sec |
| Latency (TTFT) | 2.41s |
| Input price | $0.38 / 1M tokens |
| Output price | $2.25 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 36B |
| Reasoning | No |
| Input modalities | text, image, video |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-6-35b-a3b-non-reasoning |
Pricing
Token prices
Price per 1M tokens
Qwen3.6 35B A3B, as listed in the catalog record
- Input$0.38
- Output$2.25
| Token type | Price per 1M |
|---|---|
| Input | $0.38 |
| Output | $2.25 |
Model Intelligence legacy profile: qwen3-6-35b-a3b-non-reasoning
FAQ · 20
Frequently asked questions
Qwen3.6 35B A3B (Non-reasoning) was released on April 16, 2026.
Qwen3.6 35B A3B (Non-reasoning) was created by Alibaba.
Qwen3.6 35B A3B (Non-reasoning) scores 24 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 6).
Qwen3.6 35B A3B (Non-reasoning) generates output at 179.9 tokens per second (based on Alibaba's API), which is well above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
Qwen3.6 35B A3B (Non-reasoning) has a time to first token (TTFT) of 2.41s (based on Alibaba's API), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 1.54s).
Qwen3.6 35B A3B (Non-reasoning) costs $0.38 per 1M input tokens (at the higher end, median: $0.15) and $2.25 per 1M output tokens (at the higher end, median: $0.32), based on Alibaba's API.
Qwen3.6 35B A3B (Non-reasoning) costs $0.38 per 1M input tokens and $2.25 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.56 per 1M tokens. Pricing may vary by provider.
No, Qwen3.6 35B A3B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3.6 35B A3B (Non-reasoning) supports text, image, and video input.
Qwen3.6 35B A3B (Non-reasoning) supports text output.
Yes, Qwen3.6 35B A3B (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Qwen3.6 35B A3B (Non-reasoning) is multimodal. It can process text, image, and video input and generate text output.
Qwen3.6 35B A3B (Non-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 (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3.6 35B A3B (Non-reasoning) has 36 billion parameters (3 billion active).
Qwen3.6 35B A3B (Non-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 (Non-reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3.6 35B A3B (Non-reasoning) achieves a score of 24 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3.6 35B A3B (Non-reasoning) is available via API through 8 providers.
Qwen3.6 35B A3B (Non-reasoning) is available through 8 API providers.