reroute

OpenAI: GPT Audio

openai/gpt-audio
Compare API Try this model

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...

Modalities
In / Out Price
$2.50 / $10 per 1M
Context
128K
Released
Jan 19, 2026
Knowledge Cutoff
—

API

Reroute speaks the OpenAI Chat Completions format. Point any OpenAI SDK at https://www.reroute.wtf/api/v1 and use openai/gpt-audio as the model.

You need an API key
Keys start with sk-rr-v1- and are shown once.
Create API key
curl https://www.reroute.wtf/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $REROUTE_API_KEY" \
  -d '{
  "model": "openai/gpt-audio",
  "messages": [
    { "role": "user", "content": "What is the meaning of life?" }
  ]
}'

Streaming

Set stream: true to receive server-sent events. The final chunk carries usage and cost.

curl -N https://www.reroute.wtf/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $REROUTE_API_KEY" \
  -d '{ "model": "openai/gpt-audio", "stream": true,
        "messages": [{ "role": "user", "content": "Count to five" }] }'