Qwen Audio 3.0 Realtime Flash · empiriolabs

Duplex speech conversation tuned for fast replies, with 19 voices, native web search, tool calling, and separate text and audio token rates.

Base modelAll models on this baseAll models of the providerto the provider

Read also: Qwen API pricing: Qwen3.8 Max, Plus, Flash, 27B and the open models at every provider

All Qwen models at every provider

Input, $/1M $0.46

Output, $/1M $1.40

Cache read $0.46

Cache write —

Context 16 384

Max output 8 192

Accepts audio, text

Last checked 04.11.2026 12:00:14 UTC

Source provider's page