Qwen3-Next 80B-A3B (Thinking) deprecated, retires 2026-10-10 → Qwen3.7 Plus

Alibaba Model Studio has deprecated Qwen3-Next 80B-A3B (Thinking), with the model set to retire on 2026-10-10 under the provider's deprecation policy. The model, listed at $0.50 per 1M input tokens and $6 per 1M output tokens with a 131k context window and 33k max output, is being replaced by Qwen3.7 Plus. Developers whose code calls the qwen3-next-80b-a3b-thinking endpoint must migrate before the retirement date.

QW✕ Retired Qwen3-Next 80B-A3B Thinking Alibaba Qwen · qwen3-next-80b-a3b-thinking Alibaba Model Studio deprecation policy: retires 2026-10-10. Provider statement → https://models.dev/alibaba/qwen3-next-80b-a3b-thinking qwentext131k context33k max out$0.50 / $6 per 1M also matches: qwen3-next-80b-a3b-thinking alibaba/qwen3-next-80b-a3b-thinking provider announcement → https://models.dev/alibaba/qwen3-next-80b-a3b-thinking Does your code call Qwen3-Next 80B-A3B Thinking ? $ curl -fsSL https://llmstatus.ai/install.sh | bash Then mm status in any repo — it finds every model you use and flags the ones on a clock. No account, nothing uploaded. Get alerted before it retires → https://llmstatus.ai/sign-up