# Qwen3-Next 80B-A3B Instruct API prices

Qwen3-Next 80B-A3B Instruct (qwen) — 262k context, 262k max output.
20 metered per-token offers from 21 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Alibaba (China) | $0.144 | $0.574 | — | 131k |
| Merge Gateway | $0.144 | $0.574 | $0.0288 | 131k |
| Kilo Gateway | $0.0975 | $0.78 | — | 262k |
| NanoGPT | $0.15 | $0.65 | $0.075 | 262k |
| Deep Infra | $0.09 | $1.1 | — | 262k |
| OpenRouter | $0.09 | $1.1 | — | 262k |
| Charm Hyper | $0.1175 | $1.136 | $0.0587 | 262k |
| Amazon Bedrock | $0.15 | $1.2 | — | 262k |
| Eden AI | $0.15 | $1.2 | — | 131k |
| DevPass (LLM Gateway) | $0.15 | $1.2 | — | 131k |
| LLM Gateway | $0.15 | $1.2 | — | 131k |
| Neon | $0.15 | $1.2 | — | 131k |
| Vercel AI Gateway | $0.15 | $1.2 | — | 131k |
| Hugging Face | $0.25 | $1 | — | 262k |
| Helicone | $0.14 | $1.4 | — | 262k |
| Jalapeno Cloud | $0.15 | $1.5 | — | 129k |
| Jiekou.AI | $0.15 | $1.5 | — | 66k |
| LLM Gateway | $0.15 | $1.5 | — | 131k |
| NovitaAI | $0.15 | $1.5 | — | 131k |
| Alibaba | $0.5 | $2 | — | 131k |

## Summary

- Cheapest input: $0.09 per 1M tokens (Deep Infra)
- Cheapest output: $0.574 per 1M tokens (Alibaba (China))
- First-party: $2 per 1M output tokens (Alibaba)
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2025-09
- Inputs: image, text, video

HTML page: https://llmprice.gitlab.io/models/qwen3-next-80b-a3b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json