Models
| Provider | Model | Input | Output | Context |
|---|---|---|---|---|
Qwen3-ASR 1.7B speech-to-text. Billed per second of audio. QwenSpeech-to-textAug 13, 2026 | PriceUsage-based | Context- | ||
Qwen3-ASR 0.6B speech-to-text. Billed per second of audio. QwenSpeech-to-textAug 13, 2026 | PriceUsage-based | Context- | ||
Qwen Audio 3.0 TTS Plus text-to-speech. Billed per input character; each Chinese (Han) character counts as 2. QwenText-to-speechJul 23, 2026 | PriceUsage-based | Context- | ||
Qwen Audio 3.0 TTS Flash text-to-speech. Billed per input character; each Chinese (Han) character counts as 2. QwenText-to-speechJul 23, 2026 | PriceUsage-based | Context- | ||