Qwen Flash
Alibaba · Efficient Qwen model for fast chat, extraction, and high-volume workloads
Key facts
- Provider
- Alibaba
- Context window
- 1M tokens
- Max output
- 32.8K tokens
- Input price
- $0.05 / M tok
- Output price
- $0.4 / M tok
- Knowledge cutoff
- Apr 2024
- Released
- Jul 28, 2025
- License
- —
Capabilities
ReasoningTool callingStructured outputFile attachmentsTemperature controlOpen weights
Reasoning options
- toggle
- budget_tokens
Pricing
USD per million tokens, list API rates.
- Input
- $0.05
- Output
- $0.4
- Cache read
- —
- Cache write
- —
Modalities
- Input
- Text
- Output
- Text