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...
Code Examples
import requests
response = requests.post(
"https://neurongate.net/v1/chat/completions",
headers={
"Authorization": "Bearer ng-your-api-key",
"Content-Type": "application/json"
},
json={
"model": "openai/gpt-audio",
"messages": [
{"role": "user", "content": "Hello!"}
]
}
)
print(response.json()["choices"][0]["message"]["content"])Pricing Details
| Example | Cost |
|---|---|
| 1K input tokens (short prompt) | $0.00250 |
| 1K in + 500 out (typical response) | $0.00750 |
| 10K in + 2K out (document analysis) | $0.0450 |
| 100K in + 10K out (large context) | $0.3500 |
Prices in USD. Billed per actual token usage. Prepay with USDT, USDC, ETH, or BTC.
Frequently Asked Questions
Capabilities
Context Window
~96K words of text
Modalities
Related Blog Posts
GPT-5.6 Is a Tool-Heavy Workflow Signal
A July 2026 analysis of GPT-5.6, lightweight programs, tool coordination, and what gateways need to track.
GPT-5.5 Made Pricing Policy More Important
An April 2026 analysis of GPT-5.5, premium pricing, 1M context, and the need for model-specific access rules.
GPT-5.4 Shifted Professional Workloads Upmarket
A March 2026 GPT-5.4 analysis focused on professional work, coding, tool use, and model tier decisions.