GPT Audio
OpenAI GPT Audio — pricing, 128k context window, API cost calculator and alternatives.
By OpenAI
Specs
- Provider
- OpenAI
- Slug
- openai/gpt-audio
- Capabilities
- tools, json_mode
Pricing freshness
- Tier
- standard
- Currency
- USD
- As of
- 2026-05-08 17:08 UTC
Pricing history
Tracking GPT Audio pricing since 2026-05-08. We'll plot the chart here once it changes.
Quickstart — call GPT Audio from your app
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-audio",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Official docs: https://platform.openai.com/docs/api-reference/chat
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.openai.com/v1",
api_key=os.environ["OPENAI_API_KEY"],
)
resp = client.chat.completions.create(
model="gpt-audio",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
Official docs: https://platform.openai.com/docs/api-reference/chat
// npm install openai
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openai.com/v1",
apiKey: process.env.OPENAI_API_KEY,
});
const resp = await client.chat.completions.create({
model: "gpt-audio",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);
Official docs: https://platform.openai.com/docs/api-reference/chat
Related models
Similar capabilities, context window, and price tier — drawn from across the catalog so you can compare alternatives in one click.
Frequently asked questions
What is GPT Audio?
GPT Audio is a large language model API from OpenAI with a 128k-token context window. It costs $2.5 per 1M input tokens and $10 per 1M output tokens.
How much does GPT Audio cost?
GPT Audio is priced at $2.5 per 1M input tokens and $10 per 1M output tokens via the OpenAI API. A 50/50 input/output workload of 1M total tokens costs about $6.25.
What is the context window of GPT Audio?
GPT Audio supports up to 128k tokens of context per request — roughly 256 pages of English text or 16000 lines of code at a typical density.
Does GPT Audio support vision, tool use, or JSON mode?
GPT Audio supports tool/function calling and structured JSON mode. It does not support image input (vision).
Who makes GPT Audio?
GPT Audio is built and operated by OpenAI. Pricing, context window, and capabilities on this page are refreshed nightly from OpenAI's public catalog.
Can I self-host GPT Audio?
GPT Audio is API-only — its weights are not publicly distributed by OpenAI, so it cannot be self-hosted today.