GPT Audio API Pricing
As of October 10, 2026, GPT Audio costs $2.50 per 1M input tokens and $10.00 per 1M output tokens on OpenAI. It has a 128,000-token context window and returns up to 16,384 tokens per response.
gpt-audio.- Input
- $2.50 / 1M tokens
- Output
- $10.00 / 1M tokens
- Context window
- 128,000 tokens
- Max output
- 16,384 tokens
- Providers
- 2
- Added to LiteLLM
- November 2025
GPT Audio pricing by provider
4 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| OpenAI | gpt-audio | $2.50 | $10.00 | 128K |
| OpenAIsnapshot 2025-08-28 | gpt-audio-2025-08-28 | $2.50 | $10.00 | 128K |
| Azure OpenAI | azure/gpt-audio | $2.50 | $10.00 | 128K |
| Azure OpenAIsnapshot 2025-08-28 | azure/gpt-audio-2025-08-28 | $2.50 | $10.00 | 128K |
Other GPT Audio prices on OpenAI
| Audio input | $32.00 per 1M tokens |
| Audio output | $64.00 per 1M tokens |
What GPT Audio costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| OpenAI | $10.00 |
| Azure OpenAI | $10.00 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| OpenAI | $27.00 |
| Azure OpenAI | $27.00 |
GPT Audio features
Input: text, audio. Output: text, audio.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- Audio input
- Audio output
- Reasoning
- Prompt caching
Use GPT Audio with LiteLLM
Call GPT Audio through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="gpt-audio",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-audio
litellm_params:
model: gpt-audio
api_key: os.environ/OPENAI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-audio",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT Audio FAQ
How much does GPT Audio cost?
GPT Audio costs $2.50 per 1M input tokens and $10.00 per 1M output tokens on OpenAI.
What is the context window of GPT Audio?
GPT Audio has a 128,000-token context window and returns up to 16,384 tokens per response.
Which providers offer GPT Audio?
GPT Audio is available from 2 providers through LiteLLM: OpenAI and Azure OpenAI.
How do I call GPT Audio with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gpt-audio", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does GPT Audio support?
GPT Audio supports function calling, parallel tool calls, audio input and audio output. It does not support structured output, image input, reasoning and prompt caching.
When did LiteLLM add GPT Audio?
GPT Audio was added to LiteLLM's model price file in November 2025.
Is GPT Audio being deprecated?
OpenAI lists a deprecation date of January 20, 2027 for gpt-audio.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- developers.openai.com/api/docs/pricing
- learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure
LiteLLM docs: OpenAI, Azure OpenAI.
Provider pages: OpenAI, Azure OpenAI.
