GPT-4o Mini Realtime Preview API Pricing Calculator

Track GPT-4o-Mini-Realtime-Preview pricing and set alerts for OpenAI’s lightweight, low-latency model optimized for real-time AI interactions.

GPT-4o Mini Realtime Preview, a multimodal model from OpenAI released 17 December 2024, has been deprecated. It was replaced by GPT Realtime Mini on 7 May 2026. The context window holds 128,000 tokens, with up to 16,384 returned per response.

Not currently offered by any tracked provider. Who stopped, and its last prices

Last updated Sep 27, 2026

Never miss an AI pricing or launch update

Get notified about new model launches, pricing changes, provider updates, deprecations, and cost-saving insights.

🔒 We respect your privacy. Unsubscribe anytime.

Model Details

Released
Dec 17, 2024
Status
Deprecated(on May 07, 2026)
Context Length
128,000
Max Output
16,384
Superseded By
GPT Realtime Mini

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

GPT-4o-Mini-Realtime-Preview is a compact, cost-efficient version of OpenAI’s real-time model, balancing performance and affordability for continuous, low-latency AI interactions. It supports multimodal input and rapid streaming output.

Perfect Fit For:
- Voice chatbots and personal assistants
- Real-time tutoring or translation tools
- Lightweight interactive applications with strict latency needs
- Cost-sensitive prototypes or small-scale deployments

Quick Model Estimate

(USD 10.0000 per 1M tokens)
(USD 20.0000 per 1M tokens)

Your GPT-4o Mini Realtime Preview Cost Estimate

💰 Total Cost

—

for 1000 input + 1000 output tokens

📥 Input (1000 × $10.000000) —
📤 Output (1000 × $20.000000) —

Cost Breakdown

📥 Input 📤 Output

At the last price OpenAI charged, before it stopped on 7th May 2026. No longer on offer.

Estimate with GPT Realtime Mini →

Pricing

No provider we track currently offers GPT-4o Mini Realtime Preview.

No longer offered by

The last prices each provider charged for GPT-4o Mini Realtime Preview before it stopped offering it. These are no longer on offer. Each row links to that provider's price history.

Provider ↕
Ended ↕
Modality ↕
Service Tier ↕
Input Price
(per 1M tokens) ↕
Output Price
(per 1M tokens) ↕
Cached Input
(per 1M tokens) ↕
Context Size ↕
View
OpenAI LogoOpenAI7th May 2026Model retiredAudioStandard$10.0000$20.0000$0.3000128,000 tokens→
OpenAI LogoOpenAI7th May 2026Model retiredTextStandard$0.6000$2.4000$0.3000128,000 tokens→

Recent changes

When GPT-4o Mini Realtime Preview was newly listed on a provider, moved to legacy or deprecated, or retired.

  1. Retired

    OpenAI retired GPT-4o Mini Realtime Preview, with GPT Realtime Mini as the suggested replacement.

See all changes, new releases and retirements →

Other Models in the GPT-4o Family

ChatGPT 4o Latest

Deprecated

Multimodal · 128,000 context

GPT-4o

Active

Multimodal · 128,000 context

GPT-4o 2024-05-13

Legacy

Multimodal · 128,000 context

GPT-4o 2024-08-06

Active

Fine-tuning · 128,000 context

GPT-4o Audio Preview

Deprecated

Audio · 128,000 context

GPT-4o Mini

Active

Multimodal · 128,000 context

GPT-4o Mini 2024-07-18

Active

Fine-tuning · 127,997 context

GPT-4o Mini Audio Preview

Deprecated

Audio · 128,000 context

GPT-4o Mini Search Preview

Active

Search · 128,000 context

GPT-4o Mini Transcribe

Legacy

Audio

GPT-4o Mini TTS

Legacy

Audio

GPT-4o Realtime Preview

Deprecated

Multimodal · 128,000 context

GPT-4o Search Preview

Active

Search · 128,000 context

GPT-4o Transcribe

Legacy

Audio

GPT-4o Transcribe Diarize

Legacy

Audio

FAQs about GPT-4o Mini Realtime Preview

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

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

Is GPT-4o Mini Realtime Preview still available?

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