The gpt-audio model is our first generally available audio model. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.
function_callinghttps://api.openai.com/v1/chat/completions| Input | Cached input | Output | |
|---|---|---|---|
| Standard | $32 | — | $64 |
| Input | Cached input | Output | |
|---|---|---|---|
| Standard | $2.5 | — | $10 |
| Model | Context | Max out | Pricing |
|---|---|---|---|
| GPT-Audio Mini | 128K | 16K | $0.6$2.4 |
| GPT-Audio-1.5 | 128K | 16K | $2.5$10 |
| GPT-Audio | 128K | 16K | $2.5$10 |
/v1/models/openai/gpt-audio-1.5