GPT Audio pricing & benchmarks
Released Jan 19, 2026 · served by 1 provider
What GPT Audio is
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...
- Model ID:
openai/gpt-audio - Modality: text+audio->text+audio
- Tool calling: supported · Structured output: supported
Providers and prices for GPT Audio
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| OpenAIcheapest | $2.50 | $10.00 | 128K | — | 100.0% | — |
FAQ
How much does the GPT Audio API cost?
$2.50 per 1M input tokens and $10.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $5.50.
Is GPT Audio free?
No. It is a paid model starting at $2.50 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for GPT Audio?
OpenAI at $2.50 input / $10.00 output per 1M tokens.
Can I self-host GPT Audio?
No. GPT Audio is closed-weight and only available through hosted APIs.