GPT Realtime 2 API Pricing

As of October 10, 2026, GPT Realtime 2 costs $4.00 per 1M input tokens and $24.00 per 1M output tokens on OpenAI, with cache reads at $0.40 per 1M tokens. It has a 128,000-token context window and returns up to 32,000 tokens per response.

By OpenAIModel ID gpt-realtime-2Prices updated October 10, 2026Checked October 10, 2026

Input: $4.00 / 1M tokens
Output: $24.00 / 1M tokens
Cache read: $0.40 / 1M tokens
Context window: 128,000 tokens
Max output: 32,000 tokens
Providers: 2
Added to LiteLLM: May 2026

GPT Realtime 2 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.

Provider	Model name in LiteLLM	Input	Output	Cache read	Context
OpenAI	`gpt-realtime-2`	$4.00	$24.00	$0.40	128K
Azure OpenAI	`azure/gpt-realtime-2`	$4.00	$24.00	$0.40	32K

Other GPT Realtime 2 prices on OpenAI

Audio input	$32.00 per 1M tokens
Audio output	$64.00 per 1M tokens

What GPT Realtime 2 costs in practice

1,000 requests with 2,000 input and 500 output tokens each

OpenAI	$20.00
Azure OpenAI	$20.00

100 long-document requests with 100,000 input and 2,000 output tokens each

OpenAI	$44.80
Azure OpenAI	$44.80

GPT Realtime 2 features

Input: text, image, audio. Output: text, audio.

Function calling
Parallel tool calls
Audio input
Audio output

Use GPT Realtime 2 with LiteLLM

Call GPT Realtime 2 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.

Python SDK

from litellm import completion

response = completion(
    model="gpt-realtime-2",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: gpt-realtime-2
    litellm_params:
      model: gpt-realtime-2
      api_key: os.environ/OPENAI_API_KEY

Call the proxy

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "gpt-realtime-2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

GPT Realtime 2 FAQ

How much does GPT Realtime 2 cost?

GPT Realtime 2 costs $4.00 per 1M input tokens and $24.00 per 1M output tokens on OpenAI, with cache reads at $0.40 per 1M tokens.

What is the context window of GPT Realtime 2?

GPT Realtime 2 has a 128,000-token context window and returns up to 32,000 tokens per response.

Which providers offer GPT Realtime 2?

GPT Realtime 2 is available from 2 providers through LiteLLM: OpenAI and Azure OpenAI.

How do I call GPT Realtime 2 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gpt-realtime-2", 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 Realtime 2 support?

GPT Realtime 2 supports function calling, parallel tool calls, audio input and audio output.

When did LiteLLM add GPT Realtime 2?

GPT Realtime 2 was added to LiteLLM's model price file in May 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.