Qwen3-Next 80B-A3B Instruct
Summary
Qwen3-Next 80B-A3B Instruct is an open-weight language model from Alibaba (Qwen), released on Sept 2025. It accepts text and generates text, with a 131K-token context window and up to 33K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.09 per million input tokens and $1.10 per million output tokens (DeepInfra), across 5 providers we track. It is scheduled for retirement on 8 Oct 2026.
Qwen instruction model for multilingual chat, reasoning, and tool use
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | Sept 2025 [models.dev] |
| Status | Deprecated [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 81.3B [Hugging Face] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 33K tokens [models.dev] |
| Knowledge cutoff | Apr 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
| Retirement date | 8 Oct 2026 [OpenRouter] |
| Hugging Face | Qwen/Qwen3-Next-80B-A3B-Instruct [Hugging Face] |
Qwen3-Next 80B-A3B Instruct API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepInfra Qwen/Qwen3-Next-80B-A3B-Instruct | $0.09 | $1.10 | – | 262K | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen3-next-80b-a3b-instruct | $0.09 | $1.10 | – | 262K | OpenRouter, 18 Nov 2026 |
| Amazon Bedrock qwen.qwen3-next-80b-a3b | $0.15 | $1.20 | – | 262K | models.dev, 18 Nov 2026 |
| Vercel AI Gateway alibaba/qwen3-next-80b-a3b-instruct | $0.15 | $1.20 | – | 262K | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers Qwen/Qwen3-Next-80B-A3B-Instruct | $0.25 | $1 | – | 262K | models.dev, 18 Nov 2026 |
Running Qwen3-Next 80B-A3B Instruct locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 49 GB | 51 GB | 53 GB |
| Q8_0 (8-bit) | 86 GB | 88 GB | 90 GB |
| FP16 / BF16 (16-bit) | 163 GB | 164 GB | 167 GB |
At 4-bit with an 8K conversation, Qwen3-Next 80B-A3B Instruct needs about 51 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct has a context window of 131,072 tokens (131K) and can generate up to 32,768 tokens in a single response, according to models.dev.
How much does the Qwen3-Next 80B-A3B Instruct API cost?
Qwen3-Next 80B-A3B Instruct is listed from $0.09 per million input tokens and $1.10 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.
Is Qwen3-Next 80B-A3B Instruct open source?
Qwen3-Next 80B-A3B Instruct is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-Next-80B-A3B-Instruct under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen3-Next 80B-A3B Instruct released?
Alibaba (Qwen) released Qwen3-Next 80B-A3B Instruct on Sept 2025, according to models.dev.
Which providers offer Qwen3-Next 80B-A3B Instruct?
We track Qwen3-Next 80B-A3B Instruct on 5 providers: DeepInfra, OpenRouter, Amazon Bedrock, Vercel AI Gateway, Hugging Face Inference Providers.
How much VRAM does Qwen3-Next 80B-A3B Instruct need?
About 51 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 88 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| GLM-4.5-Air | Zhipu AI (Z.ai) | 28 Jul 2025 | 131K | $0.13 | $0.85 | Open |
| Gemma Sea Lion V4 27B It | Aisingapore | 23 Sept 2025 | 128K | $0.35 | $0.56 | Open |
| Uncensored | Cognitivecomputations | 9 Jul 2025 | 128K | $0.20 | $0.90 | Open |
| DeepSeek V3.1 | DeepSeek | 21 Aug 2025 | 164K | $0.25 | $0.95 | Open |
| DeepSeek-V3.1 | DeepSeek | 21 Aug 2025 | 164K | $0.25 | $0.95 | Open |
| Cydonia 24B V4.1 | Thedrummer | 27 Sept 2025 | 131K | $0.30 | $0.50 | Open |
Change history
- OpenRouter price changed: input $0.10 → $0.09, output $1.10 → $1.10 per 1M tokens
- OpenRouter price changed: input $0.09 → $0.10, output $1.10 → $1.10 per 1M tokens
- Status changed from active to deprecated
- No longer listed on alibaba
- OpenRouter price changed: input $0.10 → $0.09, output $1.10 → $1.10 per 1M tokens
- No longer listed on novita-ai
- OpenRouter price changed: input $0.15 → $0.10, output $1.50 → $1.10 per 1M tokens
- Retirement date changed from none to 8 Oct 2026
- OpenRouter price changed: input $0.10 → $0.15, output $1.10 → $1.50 per 1M tokens
Sources
- https://openrouter.ai/qwen/qwen3-next-80b-a3b-instruct
- https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3-next-80b-a3b-instruct.toml
- https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3-Next-80B-A3B-Instruct.toml
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/qwen.qwen3-next-80b-a3b.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/alibaba/qwen3-next-80b-a3b-instruct.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-Next-80B-A3B-Instruct.toml