- Fast, inexpensive, capable model ideal for replacing GPT-3.5 Turbo series models. - Text and image processing. - JSON Mode. - Parallel function calling.
function_calling| Training | Input | Cached input | Output | |
|---|---|---|---|---|
| Standard | $3 | $0.3 | $0.15 | $1.2 |
| Batch | $3 | $0.15 | $0.075 | $0.6 |
| Model | Context | Max out |
|---|---|---|
| gpt-4o-audio-preview | 128K | 16K |
| gpt-4o-mini-audio-preview | 128K | 16K |
| gpt-4o-mini-realtime-preview | 16K | 4K |
| gpt-4o-mini-transcribe | 16K | 2K |
| gpt-4o-mini-tts | — | — |
| gpt-4o-mini | 128K | 16K |
| gpt-4o-realtime-preview | 32K | 4K |
| gpt-4o-transcribe-diarize | 16K | 2K |
| gpt-4o-transcribe | 16K | 2K |
| GPT-4o, GPT-4o mini, and GPT-4 Turbo | 128K | 16K |
/v1/models/azure/gpt-4o-mini