GPT Realtime Mini Pricing - Cost Calculator

Track gpt-realtime-mini pricing with instant alerts, compare provider rates easily, and stay ahead of fluctuations affecting real-time multimodal applications.

GPT Realtime Mini is a legacy multimodal model from OpenAI, kept available since its release on 6 October 2025. It replaced GPT-4o Mini Realtime Preview, and is due to be replaced by GPT Realtime 2.1 Mini on 20 January 2027. A 32,000-token context window feeds responses of up to 4,096 tokens. It costs between $0.60 and $10.00 per million input tokens, depending on service tier.

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
Oct 6, 2025
Status
Legacysunset Jan 20, 2027
Context Length
32,000
Max Output
4,096
Superseded By
GPT Realtime 2.1 Mini

Where is GPT Realtime Mini a perfect fit?

gpt-realtime-mini is built for low-latency, streaming, multimodal interactions where speed and responsiveness matter more than deep reasoning. Ideal for:
- Live voice assistants with near-instant responses
- Interactive front-end agents in apps and websites
- Real-time transcription + generation workflows
- Customer support bots that need rapid turn-taking
- On-device or edge-style multimodal use cases
- Fast command execution without long model “thinking” delays
- Lightweight animation, gesture, or UI control via streaming events

Quick Model Estimate

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

Your GPT Realtime Mini Cost Estimate

💰 Total Cost

—

for 1000 input + 1000 output tokens

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

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 LogoOpenAIAudioStandard$10.0000$20.0000$0.300032,000 tokens→
OpenAI LogoOpenAIImageStandard$0.8000N/A$0.080032,000 tokens→
OpenAI LogoOpenAITextStandard$0.6000$2.4000$0.060032,000 tokens→

Other Models in the GPT Realtime Family

GPT Realtime

Legacy

Multimodal · 32,000 context

GPT Realtime Translate

Active

Audio · 16,000 context

GPT Realtime Whisper

Active

Transcription · 16,000 context

FAQs about GPT Realtime Mini

How much does GPT Realtime Mini cost per 1M tokens?

GPT Realtime Mini costs between $0.60 and $10.00 per million input tokens, and between $2.40 and $20.00 per million output tokens.

What does a typical workload cost with GPT Realtime Mini?

1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $2.40 with GPT Realtime Mini at its lowest rates. Use the calculator on this page for your own volumes.

Where can I use GPT Realtime Mini?

GPT Realtime Mini is available through OpenAI, from $0.60 per million input tokens.

What is GPT Realtime Mini's context window?

GPT Realtime Mini has a context window of 32,000 tokens, and returns up to 4,096 tokens in a single response.

Is GPT Realtime Mini still available?

GPT Realtime Mini is a legacy model and is scheduled for retirement on 20 January 2027. The replacement is GPT Realtime 2.1 Mini.