# Qwen Flash API prices

Qwen Flash (qwen) — 1.0M context, 250k max output.
8 metered per-token offers from 7 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Alibaba (China) | $0.022 | $0.216 | — | 1.0M |
| Merge Gateway | $0.022 | $0.216 | $0.0044 | 1.0M |
| Ofox | $0.022 | $0.22 | $0.0043 | 1.0M |
| Ofox | $0.022 | $0.22 | $0.0043 | 1.0M |
| Alibaba | $0.05 | $0.4 | — | 1.0M |
| DevPass (LLM Gateway) | $0.05 | $0.4 | $0.01 | 1.0M |
| LLM Gateway | $0.05 | $0.4 | $0.01 | 1.0M |
| LLMTR | $0.05 | $0.4 | — | 1.0M |

## Summary

- Cheapest input: $0.022 per 1M tokens (Alibaba (China))
- Cheapest output: $0.216 per 1M tokens (Alibaba (China))
- First-party: $0.4 per 1M output tokens (Alibaba)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-07-28
- Inputs: text

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