Audio input
Models that take audio as input, including transcription. Listed by input price, cheapest first. All 19.
| Model | Input | Output | Context | Served by |
|---|---|---|---|---|
| NVIDIA: Nemotron 3 Nano Omni (free) | $0.00 per M | $0.00 per M | 256,000 tokens | nvidia |
| Google: Gemini 3.1 Flash Lite | $0.25 per M | $1.50 per M | 1,048,576 tokens | |
| Google: Gemini 3.1 Flash Lite Preview | $0.25 per M | $1.50 per M | 1,048,576 tokens | |
| Qwen3 Omni 30B A3B Thinking | $0.25 per M | $0.97 per M | 65,536 tokens | novita |
| Google: Gemini 3.5 Flash Lite | $0.30 per M | $2.50 per M | 1,048,576 tokens | |
| Google: Gemini 3.6 Flash | $0.75 per M | $3.75 per M | 1,048,576 tokens | |
| Google: Gemini 3.7 Flash | $0.75 per M | $3.75 per M | 1,048,576 tokens | |
| Google: Gemini 3.8 Flash | $0.75 per M | $3.75 per M | 1,048,576 tokens | |
| Google Gemini Flash Latest | $0.75 per M | $3.75 per M | 1,048,576 tokens | |
| Google: Gemini 3.5 Flash | $1.50 per M | $9.00 per M | 1,048,576 tokens | |
| Google: Gemini 3.1 Pro Preview | $2.00 per M | $12.00 per M | 1,048,576 tokens | |
| Google: Gemini 3.1 Pro Preview Custom Tools | $2.00 per M | $12.00 per M | 1,048,576 tokens | |
| Google Gemini Pro Latest | $2.00 per M | $12.00 per M | 1,048,576 tokens | |
| Qwen/Qwen3-ASR-0.6B | — | — | — | deepinfra |
| Qwen/Qwen3-ASR-1.7B | — | — | — | deepinfra |
| mistralai/Voxtral-Mini-3B-2507 | — | — | — | deepinfra |
| nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b | — | — | — | deepinfra |
| openai/whisper-large-v3 | — | — | — | deepinfra |
| openai/whisper-large-v3-turbo | — | — | — | deepinfra |
Prices are the providers' list prices per million tokens, as of , on your own provider key with no fee on the tokens.