Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | openaiOpenAI: GPT AudioRemove × |
|---|---|
| What’s different | The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced... |
| Date | Jan 19, 2026Listed |
API prices USD · provider configuration shown below | |
| Listed rate | See provider quotes |
| Provider endpoints | 0 endpoints → |
Specifications | |
| Context window | 128K |
| Max output | 16.4K |
| Parameters | — |
| Tool calling | Supported |
| Structured output | Supported |
| Audio input | Supported |