Qwen3-Next 80B-A3B Instruct

Model facts

Context window

131K tokens

Maximum output

33K tokens

Cheapest paid input

$0.144 per 1M tokens

Cheapest paid output

$0.574 per 1M tokens

Open weights

yes

Providers

22

Capabilities and modalities

tool calling, structured output, temperature control, open weights, text, image, video.

Local hardware estimate

At 4K context: Q4_K_M 44.0 GiB, Q8_0 81.8 GiB, F16 152.8 GiB working memory.

Parameters

81.3 billion

Architecture

qwen3next

Model license

apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

Observed price history

• 2026-08-24: $0.144 input / $0.574 output per 1M tokens

API providers

• Nvidia — model id qwen/qwen3-next-80b-a3b-instruct; free input / free output per 1M tokens; provider documentation
• Alibaba (China) — model id qwen3-next-80b-a3b-instruct; $0.144 input / $0.574 output per 1M tokens; provider documentation
• Merge Gateway — model id qwen/qwen3-next-80b-a3b-instruct; $0.144 input / $0.574 output per 1M tokens; provider documentation
• NanoGPT — model id qwen/Qwen3-Next-80B-A3B-Instruct; $0.15 input / $0.65 output per 1M tokens; provider documentation
• Kilo Gateway — model id qwen/qwen3-next-80b-a3b-instruct; $0.098 input / $0.78 output per 1M tokens; provider documentation
• Deep Infra — model id Qwen/Qwen3-Next-80B-A3B-Instruct; $0.09 input / $1.1 output per 1M tokens; provider documentation
• OpenRouter — model id qwen/qwen3-next-80b-a3b-instruct; $0.1 input / $1.1 output per 1M tokens; provider documentation
• Hugging Face — model id Qwen/Qwen3-Next-80B-A3B-Instruct; $0.25 input / $1 output per 1M tokens; provider documentation
• Charm Hyper — model id qwen3-next-80b-a3b-instruct; $0.117 input / $1.14 output per 1M tokens; provider documentation
• DevPass (LLM Gateway) — model id qwen3-next-80b-a3b-instruct; $0.15 input / $1.2 output per 1M tokens; provider documentation
• Eden AI — model id qwen/qwen3-next-80b-a3b-instruct; $0.15 input / $1.2 output per 1M tokens; provider documentation
• LLM Gateway — model id vertex-openai/qwen3-next-80b-a3b-instruct; $0.15 input / $1.2 output per 1M tokens; provider documentation
• Neon — model id qwen3-next-80b-a3b-instruct; $0.15 input / $1.2 output per 1M tokens; provider documentation
• Vercel AI Gateway — model id alibaba/qwen3-next-80b-a3b-instruct; $0.15 input / $1.2 output per 1M tokens; provider documentation
• Helicone — model id qwen3-next-80b-a3b-instruct; $0.14 input / $1.4 output per 1M tokens; provider documentation
• Jalapeno Cloud — model id Qwen3-Next-80B-A3B-Instruct; $0.15 input / $1.5 output per 1M tokens; provider documentation
• Jiekou.AI — model id qwen/qwen3-next-80b-a3b-instruct; $0.15 input / $1.5 output per 1M tokens; provider documentation
• LLM Gateway — model id novita/qwen3-next-80b-a3b-instruct; $0.15 input / $1.5 output per 1M tokens; provider documentation
• NovitaAI — model id qwen/qwen3-next-80b-a3b-instruct; $0.15 input / $1.5 output per 1M tokens; provider documentation
• Alibaba — model id qwen3-next-80b-a3b-instruct; $0.5 input / $2 output per 1M tokens; provider documentation
• Arena — model id qwen3-next-80b-a3b-instruct; not published input / not published output per 1M tokens; provider documentation
• Qiniu — model id qwen3-next-80b-a3b-instruct; not published input / not published output per 1M tokens; provider documentation