# Qwen3 Next 80B A3B Thinking API prices

Qwen3 Next 80B A3B Thinking (qwen) — 262k context, 131k max output.
5 metered per-token offers from 6 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| LLM Gateway | $0.15 | $1.2 | — | 131k |
| Vercel AI Gateway | $0.15 | $1.2 | — | 131k |
| Jiekou.AI | $0.15 | $1.5 | — | 66k |
| NovitaAI | $0.15 | $1.5 | — | 131k |
| Hugging Face | $0.3 | $2 | — | 262k |

## Summary

- Cheapest input: $0.15 per 1M tokens (LLM Gateway)
- Cheapest output: $1.2 per 1M tokens (LLM Gateway)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-09
- Inputs: text

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