GPT-4o Realtime Preview Pricing - Cost Calculator

Model Details

Released

Oct 1, 2024

Status

Deprecated(on May 07, 2026)

Context Length

128,000

Max Output

16,384

Superseded By

GPT Realtime 1.5

Where is GPT-4o Realtime Preview a perfect fit?

GPT-4o-Realtime-Preview is an early access, streaming-enabled multimodal model built for interactive, real-time AI conversations. It delivers rapid, continuous responses across text, vision, and audio inputs, ideal for latency-sensitive use cases.

Perfect Fit For:
- Real-time conversational AI and voice assistants
- Interactive customer support and sales tools
- Live educational, translation, or co-creation experiences
- AI-driven meetings or commentary platforms

Quick Model Estimate

Tokens Characters Words

Model

Provider

Modality

Service Tier

Context Size

Input Tokens

(USD 40.0000 per 1M tokens)

Output Tokens

(USD 80.0000 per 1M tokens)

No. of API Calls

Your GPT-4o Realtime Preview Cost Estimate

💰 Total Cost

—

for 1000 input + 1000 output tokens

📥 Input (1000 × $40.000000) —

📤 Output (1000 × $80.000000) —

Cost Breakdown

📥 Input 📤 Output

Prices are watched for changes and checked against the provider's own page.

Pricing

Provider ↕	Modality ↕	Service Tier ↕	Input Price (per 1M tokens) ↕	Output Price (per 1M tokens) ↕	Cached Input (per 1M tokens) ↕	Context Size ↕	View
OpenAI	Audio	Standard	$40.0000	$80.0000	$2.5000	128,000 tokens	→
OpenAI	Text	Standard	$5.0000	$20.0000	$2.5000	128,000 tokens	→

Audio

FAQs about GPT-4o Realtime Preview

How much does GPT-4o Realtime Preview cost per 1M tokens?

GPT-4o Realtime Preview costs between $5.00 and $40.00 per million input tokens, and between $20.00 and $80.00 per million output tokens.

What does a typical workload cost with GPT-4o Realtime Preview?

1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $20.00 with GPT-4o Realtime Preview at its lowest rates. Use the calculator on this page for your own volumes.

Where can I use GPT-4o Realtime Preview?

GPT-4o Realtime Preview is available through OpenAI, from $5.00 per million input tokens.

What is GPT-4o Realtime Preview's context window?

GPT-4o Realtime Preview has a context window of 128,000 tokens, and returns up to 16,384 tokens in a single response.

Is GPT-4o Realtime Preview still available?

GPT-4o Realtime Preview is deprecated and was retired on 7 May 2026. The replacement is GPT Realtime 1.5.