Qwen3-Next-80B-A3B-Instruct
by Nvidia · family qwen · listed Dec 2024T
Qwen instruction model for multilingual chat, reasoning, and tool use
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
qwen/qwen3-next-80b-a3b-instruct- Context window
- 262K tokens
- Max output
- 16K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Dec 2024
- Released
- 2024-12-01
- Last updated
- 2025-09-05
- Provider docs
- docs.api.nvidia.com/nim/
Back of the envelope
≈
Also listed at
- Deep Infra$0.09 in · $1.10 out
- Kilo Gateway$0.09 in · $1.10 out
- OpenRouter$0.09 in · $1.10 out
- IO.NET$0.10 in · $0.80 out
- Helicone$0.14 in · $1.40 out
- Alibaba (China)$0.144 in · $0.574 out
- Vercel AI Gateway$0.15 in · $1.20 out
- NovitaAI$0.15 in · $1.50 out
- LLM Gateway$0.15 in · $1.20 out
- Jiekou.AI$0.15 in · $1.50 out
- NanoGPT$0.15 in · $0.65 out
- Hugging Face$0.25 in · $1.00 out
- Alibaba$0.50 in · $2.00 out
- Qiniu— in · — out