Model Library
AlibabaReleased September 11, 2025Qwen3 Next 80B A3B
Alibaba · Released September 11, 2025
Intelligence score
17
At a glance
- Intelligence
- 17
- Speed
- 114.9tokens/sec
- Latency
- 2.34stime to first token
- Input price
- $0.50per 1M tokens
- Output price
- $6.00per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 80billions
Summary
Comparison summary
Qwen3 Next 80B A3B (Reasoning) scores 17 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). Qwen3 Next 80B A3B (Reasoning) generates output at 114.9 tokens per second (based on Alibaba's API), which is above average compared to other open weight models of similar size (median: 88.2 t/s). Qwen3 Next 80B A3B (Reasoning) costs $0.50 per 1M input tokens (somewhat higher than average, median: $0.40) and $6.00 per 1M output tokens (at the higher end, median: $0.84), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 Next 80B A3B |
|---|---|
| Provider | Alibaba |
| Release date | September 11, 2025 |
| Intelligence score | 17 |
| Speed | 114.9 tokens/sec |
| Latency (TTFT) | 2.34s |
| Input price | $0.50 / 1M tokens |
| Output price | $6.00 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 80B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-next-80b-a3b-reasoning |
Pricing
Token prices
Price per 1M tokens
Qwen3 Next 80B A3B, as listed in the catalog record
- Input$0.50
- Output$6.00
| Token type | Price per 1M |
|---|---|
| Input | $0.50 |
| Output | $6.00 |
Model Intelligence legacy profile: qwen3-next-80b-a3b-reasoning
FAQ · 21
Frequently asked questions
Qwen3 Next 80B A3B (Reasoning) was released on September 11, 2025.
Qwen3 Next 80B A3B (Reasoning) was created by Alibaba.
Qwen3 Next 80B A3B (Reasoning) scores 17 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Qwen3 Next 80B A3B (Reasoning) generates output at 114.9 tokens per second (based on Alibaba's API), which is above average compared to other open weight models of similar size (median: 88.2 t/s).
Qwen3 Next 80B A3B (Reasoning) has a time to first token (TTFT) of 2.34s (based on Alibaba's API), which is somewhat higher than average compared to other open weight models of similar size (median: 1.52s).
Qwen3 Next 80B A3B (Reasoning) costs $0.50 per 1M input tokens (somewhat higher than average, median: $0.40) and $6.00 per 1M output tokens (at the higher end, median: $0.84), based on Alibaba's API.
Qwen3 Next 80B A3B (Reasoning) costs $0.50 per 1M input tokens and $6.00 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.05 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Qwen3 Next 80B A3B (Reasoning) generated 59M output tokens, which is better than average compared to other open weight models of similar size (median: 59M).
Yes, Qwen3 Next 80B 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 Next 80B A3B (Reasoning) supports text input.
Qwen3 Next 80B A3B (Reasoning) supports text output.
No, Qwen3 Next 80B A3B (Reasoning) does not support image input. It can only process text.
No, Qwen3 Next 80B A3B (Reasoning) is not multimodal. It only supports text input.
Qwen3 Next 80B 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 Next 80B A3B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 Next 80B A3B (Reasoning) has 80 billion parameters (3 billion active).
Qwen3 Next 80B A3B (Reasoning) is a Mixture of Experts (MoE) model with 80 billion total parameters, but only 3 billion active parameters are used during inference.
Qwen3 Next 80B A3B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 Next 80B A3B (Reasoning) achieves a score of 17 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 Next 80B A3B (Reasoning) is available via API through 7 providers.
Qwen3 Next 80B A3B (Reasoning) is available through 7 API providers.