AI Observatory / Model Radar
OpenAI / openai/gpt-audio
OpenAI: GPT Audio
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...
128,000
Context
16,384
Max output
$2.50 / 1M
Prompt price
2026-01-19
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | OpenAI | Input modalities | text, audio |
|---|---|---|---|
| Output modalities | text, audio | Prompt price | $2.50 / 1M |
| Completion price | $10.00 / 1M | Request price | N/A |
| Context length | 128,000 | Max completion tokens | 16,384 |
| Supported parameters | frequency_penalty, logit_bias, logprobs, max_tokens, presence_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p | ||
Best for
openai/gpt-audio
OpenAI: GPT Audio
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...
Coding workflows
Cross-modal work
Voice and audio
new
tool-capable
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.