OpenAIPremium+ plan
GPT Audio 1.5
OpenAI's full-size audio-native chat model. Replies in text and speech in chat completions. OpenAI's recommended replacement for GPT Audio mini, which shuts down January 20, 2027. Does not support web search.
You always get the exact model you pick — we never silently route you to another.
Specifications
| Provider | OpenAI |
|---|---|
| Released | 2026-02-23 |
| Context window | 128,000 tokens |
| Max output | 16,384 tokens |
| Knowledge cutoff | September 30, 2024 |
| Input price | $2.50 / 1M tokens |
| Output price | $10.00 / 1M tokens |
| Request cost | 5 premium requests |
| Plan tier | Premium+ |
| Input | Text, Audio |
| Output | Text, Audio |
| Features | Audio: $32.00 input and $64.00 output per 1M tokens (about 20 audio tokens per second of speech), 5 premium requests per send before length multipliers, Function calling supported |
| API endpoints | v1/chat/completions |
| Model ID | gpt-audio-1.5 |