Qwen 3.5 Flash
Qwen 3.5 Flash is Alibaba's production-hosted multimodal model built on a hybrid linear-attention MoE architecture, offering a context window of 1M tokens and sub-second responsiveness for high-throughput agentic workloads.
Vision (Image)Explicit CachingFile InputReasoningTool Use
index.ts
import { streamText } from 'ai'
const result = streamText({ model: 'alibaba/qwen3.5-flash', prompt: 'Why is the sky blue?'})More models by Alibaba
| Model |
|---|
| 1M | 2.8s | 55tps | $0.40/MFree | $1.60/MFree | Read: $0.08/MFree Write: $0.5/MFree | — | — | +3 |  | 06/01/2026 | |||
| 991K | 3.0s | 78tps | $1.25/MFree | $3.75/MFree | Read:$0.25/MFree Write:$1.56/MFree | — | — | +3 | | 05/21/2026 | |||
| 1M | 0.4s | 109tps | $0.50/M | $3.00/M | Read: $0.1/M Write: $0.63/M | — | — | +3 |  | 04/02/2026 | |||
| 131K | 0.2s | 407tps | $0.10/M | $0.30/M | Read:$0.14/M Write:— | — | — |   +1 | 04/01/2025 | ||||
| 262K | 0.5s | 82tps | $0.07/M | $0.46/M | — | — |   | 04/01/2025 | |||||
| 41K | 0.3s | 49tps | $0.12/M | $0.24/M | — | — | | 04/01/2025 |
