OpenAIGPT-4oTool use

Gpt 4o Realtime Preview pricing

If you are budgeting for Gpt 4o Realtime Preview, start with the numbers below. We index 1 provider price. Cheapest input is $5.00 per million tokens. Cheapest output is $20.00 per million tokens. The model lists a 128K context window in our data.

128K context·1 provider·verified Mar 13, 2026
Best input$5.00per 1M tokens · OpenAI
Best output$20.00per 1M tokens · OpenAI

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 1 offer is listed for Gpt 4o Realtime Preview. Best input in this view: OpenAI.

O
OpenAInative
Input / 1M
$5.00
Output / 1M
$20.00
Cached in: $2.50

Input vs output · 1M tokens

Cost calculator

The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Gpt 4o Realtime Preview cost scales with traffic.

In: $5.00/M·Out: $20.00/M·Cache: $2.50/M

0.500000¢ / req

1.000000¢ / req

Daily
$150
Monthly
$4.5K
Annual
$54.8K

Model specifications

Quick spec sheet for Gpt 4o Realtime Preview before you dive back into pricing. Family: GPT-4o. Reported under OpenAI.

Context window
128,000 tokens
Max output
4,096 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
N/A
Primary provider
OpenAI
Model family
GPT-4o

Compare Gpt 4o Realtime Preview

Open a pair page to see Gpt 4o Realtime Preview next to another model with a shared provider matrix. 6 shortcuts below.

Frequently asked questions

Answers pull from the same numbers you see on this page.

Gpt 4o Realtime Preview costs $5.00 per million input tokens and $20.00 per million output tokens via the native API. Prompt caching reduces input costs to $2.50/M tokens.

Also from OpenAI

Other models by OpenAI with live pricing in our catalog.