GPT-4o Realtime Preview API Pricing
As of October 10, 2026, GPT-4o Realtime Preview costs $5.00 per 1M input tokens and $20.00 per 1M output tokens on Azure OpenAI, with cache reads at $2.50 per 1M tokens. It has a 128,000-token context window and returns up to 4,096 tokens per response.
azure/gpt-4o-realtime-preview-2024-10-01.- Input
- $5.00 / 1M tokens
- Output
- $20.00 / 1M tokens
- Cache read
- $2.50 / 1M tokens
- Context window
- 128,000 tokens
- Max output
- 4,096 tokens
- Providers
- 1
- Added to LiteLLM
- December 2024
GPT-4o Realtime Preview pricing by provider
6 listings across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| Azure OpenAIsnapshot 2024-10-01 | azure/gpt-4o-realtime-preview-2024-10-01 | $5.00 | $20.00 | $2.50 | 128K |
| Azure OpenAIsnapshot 2024-12-17 | azure/gpt-4o-realtime-preview-2024-12-17 | $5.00 | $20.00 | $2.50 | 16K |
| Azure OpenAIeu, snapshot 2024-10-01 | azure/eu/gpt-4o-realtime-preview-2024-10-01 | $5.50 | $22.00 | $2.75 | 128K |
| Azure OpenAIeu, snapshot 2024-12-17 | azure/eu/gpt-4o-realtime-preview-2024-12-17 | $5.50 | $22.00 | $2.75 | 16K |
| Azure OpenAIus, snapshot 2024-10-01 | azure/us/gpt-4o-realtime-preview-2024-10-01 | $5.50 | $22.00 | $2.75 | 128K |
| Azure OpenAIus, snapshot 2024-12-17 | azure/us/gpt-4o-realtime-preview-2024-12-17 | $5.50 | $22.00 | $2.75 | 16K |
Other GPT-4o Realtime Preview prices on Azure OpenAI
| Audio input | $100.00 per 1M tokens |
| Audio output | $200.00 per 1M tokens |
What GPT-4o Realtime Preview costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Azure OpenAI | $20.00 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Azure OpenAI | $54.00 |
GPT-4o Realtime Preview features
- Function calling
- Parallel tool calls
- Audio input
- Audio output
Use GPT-4o Realtime Preview with LiteLLM
Call GPT-4o Realtime Preview through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/realtime. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="azure/gpt-4o-realtime-preview-2024-10-01",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-4o-realtime-preview
litellm_params:
model: azure/gpt-4o-realtime-preview-2024-10-01
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-4o-realtime-preview",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT-4o Realtime Preview FAQ
How much does GPT-4o Realtime Preview cost?
GPT-4o Realtime Preview costs $5.00 per 1M input tokens and $20.00 per 1M output tokens on Azure OpenAI, with cache reads at $2.50 per 1M tokens.
What is the context window of GPT-4o Realtime Preview?
GPT-4o Realtime Preview has a 128,000-token context window and returns up to 4,096 tokens per response.
Which providers offer GPT-4o Realtime Preview?
GPT-4o Realtime Preview is available from Azure OpenAI through LiteLLM, using the model name azure/gpt-4o-realtime-preview-2024-10-01.
How do I call GPT-4o Realtime Preview with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="azure/gpt-4o-realtime-preview-2024-10-01", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/realtime from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does GPT-4o Realtime Preview support?
GPT-4o Realtime Preview supports function calling, parallel tool calls, audio input and audio output.
When did LiteLLM add GPT-4o Realtime Preview?
GPT-4o Realtime Preview was added to LiteLLM's model price file in December 2024.
Is GPT-4o Realtime Preview being deprecated?
Azure OpenAI deprecated azure/gpt-4o-realtime-preview-2024-10-01 on March 26, 2025.
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:
- learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models
- learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure
- azure.microsoft.com/en-us/pricing/details/azure-openai/
LiteLLM docs: Azure OpenAI.
Provider pages: Azure OpenAI.
