Model by Alibaba (Qwen)

Qwen3 Coder Next

Qwen3 Coder Next is an open-weight coding model from Alibaba's Qwen team, and it suits people who want a capable agent model they can run on their own hardware.

Checked 2026-11-05

Qwen3 Coder Next is an open-weight coding model from Alibaba's Qwen team, and it suits people who want a capable agent model they can run on their own hardware. The Hugging Face card describes a sparse mixture-of-experts design with 80B total parameters and only 3B active per token, under the Apache 2.0 licence. Its native context is 262,144 tokens, and the card dates the release to 3 February 2026. OpenRouter lists it from 4 February 2026 at $0.12 per million input tokens and $0.80 per million output tokens, text in and text out. The catch is that it supports only non-thinking mode, so it will not emit reasoning blocks, and the card asks for a recent SGLang or vLLM build to serve it. The card also suggests cutting the context to about 32,768 tokens if memory runs out. Figures come from the Hugging Face card and the OpenRouter model list. We have not run it ourselves. We would try it first as a cheap coding backend behind an agent, then compare it with a larger model on our own repo before trusting it with long tasks.

Mentioned here

Questions

What is the context window of Qwen3 Coder Next?

262,144 tokens, with up to 235,929 tokens of output.

How much does Qwen3 Coder Next cost?

$0.12 per million input tokens and $0.8 per million output tokens, checked 31 October 2026.

Can I run Qwen3 Coder Next on my own hardware?

Yes, the weights are published under the Apache 2.0 licence. They are on huggingface.co.

Who makes Qwen3 Coder Next?

Alibaba (Qwen) makes it, and released it on 4 February 2026.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Similar

  • Qwen3.8 2.4T A95B

    Qwen3.8 2.4T A95B is the open-weight version of Alibaba's Qwen3.8 Max, for teams with a serious GPU cluster who want a frontier-size model they can host.

    • Open weights

    Alibaba (Qwen), 1M context, $2 in / 1M

  • Qwen3.7 Max

    Qwen3.7 Max is Alibaba's closed flagship text model from the Qwen3.7 series, aimed at agent, coding and office work for people who will pay for a hosted API rather than run weights.

    • Closed

    Alibaba (Qwen), 1M context, $1.48 in / 1M

  • Qwen3.7 Plus

    Qwen3.7 Plus is Alibaba's hosted multimodal model, and it suits teams that want image and video understanding plus agent tool use through an API rather than downloadable weights.

    • Closed

    Alibaba (Qwen), 1M context, $0.32 in / 1M

  • Qwen3.8 Omni Flash

    Qwen3.8 Omni Flash is Alibaba's omni-modal reasoning model, described by OpenRouter as the first Qwen model built around agentic capabilities with native audio and video understanding.

    • Closed

    Alibaba (Qwen), 1M context, $0.15 in / 1M

  • Qwen3.8 Max Prime

    Qwen3.8 Max Prime is a higher-throughput version of Alibaba's Qwen3.8 Max, sold as its own SKU at a higher price.

    • Closed

    Alibaba (Qwen), 1M context, $4 in / 1M