Model Library
AlibabaReleased September 11, 2025Qwen3 Next 80B A3B
Alibaba · Released September 11, 2025
Intelligence score
14
At a glance
- Intelligence
- 14
- Speed
- 193.0tokens/sec
- Latency
- 2.31stime to first token
- Input price
- $0.50per 1M tokens
- Output price
- $2.00per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 80billions
Summary
Comparison summary
Qwen3 Next 80B A3B Instruct scores 14 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 7). Qwen3 Next 80B A3B Instruct generates output at 193.0 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: 81.5 t/s). Qwen3 Next 80B A3B Instruct costs $0.50 per 1M input tokens (better than average, median: $0.53) and $2.00 per 1M output tokens (somewhat higher than average, median: $1.05), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 Next 80B A3B |
|---|---|
| Provider | Alibaba |
| Release date | September 11, 2025 |
| Intelligence score | 14 |
| Speed | 193.0 tokens/sec |
| Latency (TTFT) | 2.31s |
| Input price | $0.50 / 1M tokens |
| Output price | $2.00 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 80B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-next-80b-a3b-instruct |
Pricing
Token prices
Price per 1M tokens
Qwen3 Next 80B A3B, as listed in the catalog record
- Input$0.50
- Output$2.00
| Token type | Price per 1M |
|---|---|
| Input | $0.50 |
| Output | $2.00 |
Model Intelligence legacy profile: qwen3-next-80b-a3b-instruct
FAQ · 20
Frequently asked questions
Qwen3 Next 80B A3B Instruct was released on September 11, 2025.
Qwen3 Next 80B A3B Instruct was created by Alibaba.
Qwen3 Next 80B A3B Instruct scores 14 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 7).
Qwen3 Next 80B A3B Instruct generates output at 193.0 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: 81.5 t/s).
Qwen3 Next 80B A3B Instruct has a time to first token (TTFT) of 2.31s (based on Alibaba's API), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 1.59s).
Qwen3 Next 80B A3B Instruct costs $0.50 per 1M input tokens (better than average, median: $0.53) and $2.00 per 1M output tokens (somewhat higher than average, median: $1.05), based on Alibaba's API.
Qwen3 Next 80B A3B Instruct costs $0.50 per 1M input tokens and $2.00 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.65 per 1M tokens. Pricing may vary by provider.
No, Qwen3 Next 80B A3B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 Next 80B A3B Instruct supports text input.
Qwen3 Next 80B A3B Instruct supports text output.
No, Qwen3 Next 80B A3B Instruct does not support image input. It can only process text.
No, Qwen3 Next 80B A3B Instruct is not multimodal. It only supports text input.
Qwen3 Next 80B A3B Instruct 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 Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 Next 80B A3B Instruct has 80 billion parameters (3 billion active).
Qwen3 Next 80B A3B Instruct 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 Instruct is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 Next 80B A3B Instruct achieves a score of 14 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 Next 80B A3B Instruct is available via API through 7 providers.
Qwen3 Next 80B A3B Instruct is available through 7 API providers.