OpenAI
OpenAI: GPT-4o Audio
The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs are currently not supported. Audio tokens are priced at $40 per million input and $80 per million output audio tokens.
| Specifications | |
|---|---|
| Provider | OpenAI |
| Input pricing | $2.50/M tokens |
| Output pricing | $10.00/M tokens |
| Context length | 128K tokens |
| Max output | 16K tokens |
| Input modalities | audiotext |
| Output modalities | textaudio |
| Tokenizer | GPT |
| Knowledge cutoff | 2023-10-31 |
| Content moderated | Yes |
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p