Capable Azure OpenAI models with multimodal versions, which can accept both text and images as input.
| Training | Input | Cached input | Output | |
|---|---|---|---|---|
| Standard | $25 | $3.75 | $1.875 | $15 |
| Batch | $25 | $2.225 | $0.9 | $12.5 |
| 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