# Qwen Max API prices

Qwen Max (qwen) — 131k context, 8k max output.
7 metered per-token offers from 6 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Alibaba (China) | $0.345 | $1.377 | — | 131k |
| Ofox | $0.35 | $1.38 | $0.069 | 33k |
| Ofox | $0.35 | $1.38 | $0.069 | 32k |
| Alibaba | $1.6 | $6.4 | — | 33k |
| Eden AI | $1.6 | $6.4 | $0.32 | 33k |
| DevPass (LLM Gateway) | $1.6 | $6.4 | — | 33k |
| LLM Gateway | $1.6 | $6.4 | — | 33k |

## Summary

- Cheapest input: $0.345 per 1M tokens (Alibaba (China))
- Cheapest output: $1.377 per 1M tokens (Alibaba (China))
- First-party: $6.4 per 1M output tokens (Alibaba)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-04-03
- Inputs: text

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