openai/gpt-audio

OpenAI: GPT Audio

Context length
128K
Input / 1M tokens
$2.50
Output / 1M tokens
$10.00
Released
2026-01-19
Modality
text+audio->text+audio

About 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...

Call OpenAI: GPT Audio

Via OpenRouter: one base URL for every provider.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio",
    "messages": [{"role": "user", "content": "Say hello"}]
  }'

Direct on OpenAI:

curl https://api.openai.com/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-audio",
    "messages": [{"role": "user", "content": "Say hello"}]
  }'

OpenAI keys

OpenRouter keys

OpenRouter keys work for openai/gpt-audio regardless of the upstream provider.