Qwen Flash
by Alibaba · qwen-flash family · released 2025-07-28
On output pricing, Qwen Flash is cheaper than 627 of the 747 priced models tracked here, at $0.4/Mtok. Its 1,000,000-token context window is larger than 671 of 876 models. Capabilities: tools, reasoning, structured output.
Specifications
| Provider | Alibaba |
| Family | qwen-flash |
| Input price | $0.05/Mtok |
| Output price | $0.4/Mtok |
| Cache read price | $0.01/Mtok |
| Cache write price | $0.0625/Mtok |
| Context window | 1,000,000 |
| Max output tokens | 32,768 |
| Input modalities | text |
| Output modalities | text |
| Capabilities | tools, reasoning, structured output |
| Knowledge cutoff | 2024-04-01 |
| Released | 2025-07-28 |
Similar models
Data synced daily from models.dev (last synced 13 hours ago). Always verify pricing with Alibaba before deploying to production.