LiteLLMModels

GPT Realtime Whisper API Pricing

As of October 10, 2026, GPT Realtime Whisper costs $0.017 per minute of audio on OpenAI. It has a 32,000-token context window and returns up to 4,096 tokens per response.

By OpenAIModel ID gpt-realtime-whisperPrices updated Checked
Per minute
$0.017
Context window
32,000 tokens
Max output
4,096 tokens
Providers
2
Added to LiteLLM
June 2026

GPT Realtime Whisper pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMPer minuteContext
OpenAIgpt-realtime-whisper$0.017–
Azure OpenAIazure/gpt-realtime-whisper$0.01732K

What GPT Realtime Whisper costs in practice

Transcribing 1,000 minutes of audio

OpenAI$17.00
Azure OpenAI$17.00

GPT Realtime Whisper features

Input: audio. Output: text.

Use GPT Realtime Whisper with LiteLLM

Call GPT Realtime Whisper through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/audio/transcriptions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import transcription

response = transcription(
    model="gpt-realtime-whisper",
    file=open("audio.mp3", "rb"),
)
Proxy config.yaml
model_list:
  - model_name: gpt-realtime-whisper
    litellm_params:
      model: gpt-realtime-whisper
      api_key: os.environ/OPENAI_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-1234" \
  -F model="gpt-realtime-whisper" \
  -F file=@audio.mp3

GPT Realtime Whisper FAQ

How much does GPT Realtime Whisper cost?

GPT Realtime Whisper costs $0.017 per minute of audio on OpenAI.

What is the context window of GPT Realtime Whisper?

GPT Realtime Whisper has a 32,000-token context window and returns up to 4,096 tokens per response.

Which providers offer GPT Realtime Whisper?

GPT Realtime Whisper is available from 2 providers through LiteLLM: OpenAI and Azure OpenAI. The lowest price is on OpenAI.

How do I call GPT Realtime Whisper with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gpt-realtime-whisper", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/audio/transcriptions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does GPT Realtime Whisper support?

GPT Realtime Whisper supports audio input.

When did LiteLLM add GPT Realtime Whisper?

GPT Realtime Whisper was added to LiteLLM's model price file in June 2026.

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:

LiteLLM docs: OpenAI, Azure OpenAI.

Provider pages: OpenAI, Azure OpenAI.