Model Details
Released
Jul 6, 2026
Context Length
128,000
Max Output
32,000
Where is GPT Realtime 2.1 Mini a perfect fit?
GPT-Realtime-2.1 mini is OpenAI’s distilled realtime reasoning model designed for faster, lower-cost voice interactions. It improves alphanumeric recognition over the earlier GPT-Realtime mini while supporting reasoning and tool use.
- High-volume speech-to-speech assistants where API cost matters
- Customer-support, sales, appointment, and call-center voice agents
- Realtime applications requiring low latency and high throughput
- Voice workflows involving function calls and external tools
- Applications handling names, numbers, confirmation codes, addresses, and other alphanumeric information
- Interactive voice experiences delivered over WebRTC, WebSocket, or SIP
- Multimodal agents combining audio conversations with text and image inputs
- Applications that need reasoning capabilities but don't require the higher-cost GPT-Realtime-2.1
- High-volume speech-to-speech assistants where API cost matters
- Customer-support, sales, appointment, and call-center voice agents
- Realtime applications requiring low latency and high throughput
- Voice workflows involving function calls and external tools
- Applications handling names, numbers, confirmation codes, addresses, and other alphanumeric information
- Interactive voice experiences delivered over WebRTC, WebSocket, or SIP
- Multimodal agents combining audio conversations with text and image inputs
- Applications that need reasoning capabilities but don't require the higher-cost GPT-Realtime-2.1
Quick Model Estimate
Your GPT Realtime 2.1 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 | Audio | Standard | $10.0000 | $20.0000 | $0.3000 | 128,000 tokens | → |
| OpenAI | Image | Standard | $0.8000 | N/A | $0.0800 | 128,000 tokens | → |
| OpenAI | Text | Standard | $0.6000 | $2.4000 | $0.0600 | 128,000 tokens | → |
Other Models in the GPT Realtime 2.1 Family
FAQs about GPT Realtime 2.1 Mini
How much does GPT Realtime 2.1 Mini cost per 1M tokens?
GPT Realtime 2.1 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 2.1 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 2.1 Mini at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use GPT Realtime 2.1 Mini?
GPT Realtime 2.1 Mini is available through OpenAI, from $0.60 per million input tokens.
What is GPT Realtime 2.1 Mini's context window?
GPT Realtime 2.1 Mini has a context window of 128,000 tokens, and returns up to 32,000 tokens in a single response.