Qwen3.5 Flash

by Qwen · chat

Qwen3.5 generation speed-optimized model with 1M context window and multimodal support. Cost-effective for high-throughput tasks including text, image, and video understanding.

Pricing

Input: $0.026277/M tokens · Output: $0.262774/M tokens

Capabilities

Vision, Function Calling, JSON Mode, Streaming

Context: 1000K tokens

Max output: 66K tokens

Routes: 1/1 healthy

Performance

TTFT: 942ms · Latency: 2260ms · Throughput: 149.6 tok/s