Qwen3-Next-80B-A3B-Thinking
Released
2025-09-11
Last refreshed
2026-10-19
Status
Researched 1d ago
Open sourceCommercial use: permittedReasoning
Alibaba releases · 53 in the last 12 months · this family litChangelog →
Specifications
- Family
- Qwen3
- Released
- 2025-09-11
- Parameters
- 80B-A3B
- Architecture
- Mixture of Experts
- Specialization
- reasoning
- Openness
- Open source
- License
- Apache 2.0OSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
Created by
Pricing
Output / 1M
$1.20
Input / 1M
$0.150
Cheapest of 4 routes · OpenRouter
Links
About
Qwen3-Next-80B-A3B-Thinking is the thinking-mode variant of Alibaba Qwen's Qwen3-Next-80B-A3B, an 80B-parameter mixture-of-experts model with 3B active parameters per token and a hybrid Gated DeltaNet + Gated Attention architecture. It was announced on 2025-09-11 alongside the Instruct variant, with Apache-2.0 open weights on Hugging Face.
Providers(4)
Compare all 4Compare API pricing across 4 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| OpenRouter | $0.150 | $1.20 | Serverless |
| Vercel AI Gateway | $0.150 | $1.20 | Serverless |
| Fireworks AI | - | - | ProvisionedPartial |
| Together AI | - | - | ProvisionedPartial |
Available via routers & gateways(1)
Capabilities
Reasoning
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
Qwen3-Next-80B-A3B-Thinkingqwen/qwen3-next-80b-a3b-thinkingCreated by
Pricing
Output / 1M
$1.20
Input / 1M
$0.150
Cheapest of 4 routes · OpenRouter
Links