# Qwen3.6 Max Preview API prices

Qwen3.6 Max Preview (qwen) — 262k context, 66k max output.
14 metered per-token offers from 13 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Kilo Gateway | $1.027 | $6.162 | — | 262k |
| OpenRouter | $1.027 | $6.162 | — | 262k |
| NanoGPT | $1.04 | $6.24 | $0.52 | 246k |
| Pioneer | $1.04 | $6.24 | $0.208 | 240k |
| AIHubMix | $1.27 | $7.61 | $0.1268 | 240k |
| Alibaba | $1.3 | $7.8 | $0.13 | 262k |
| DevPass (LLM Gateway) | $1.3 | $7.8 | $0.13 | 262k |
| LLM Gateway | $1.3 | $7.8 | $0.13 | 262k |
| EmpirioLabs AI | $1.31 | $7.88 | $1.31 | 256k |
| Merge Gateway | $1.31 | $7.88 | — | 256k |
| Alibaba (China) | $1.32 | $7.9 | $0.132 | 246k |
| Charm Hyper | $2 | $12 | $0.2 | 256k |
| Ofox | $2.15 | $12.86 | $0.2 | 262k |
| Ofox | $2.15 | $12.86 | $0.2 | 256k |

## Summary

- Cheapest input: $1.027 per 1M tokens (Kilo Gateway)
- Cheapest output: $6.162 per 1M tokens (Kilo Gateway)
- First-party: $7.8 per 1M output tokens (Alibaba)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-04-20
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/qwen3-6-max-preview/
Full dataset: https://llmprice.gitlab.io/data/catalog.json