Model Details
Released
Jul 6, 2026
Context Length
128,000
Max Output
32,000
Where is GPT Realtime 2.1 a perfect fit?
GPT-Realtime-2.1 is OpenAI's realtime reasoning model for sophisticated voice agents. It improves GPT-Realtime-2's alphanumeric recognition, silence and noise handling, and interruption behavior while adding configurable reasoning and tool use.
- Low-latency, natural speech-to-speech assistants
- Customer-service and call-center voice agents
- Voice agents requiring function calling and external tools
- Noisy environments where silence and background-noise handling matter
- Phone workflows requiring accurate recognition of names, numbers, codes, and other alphanumeric information
- Interactive applications where users frequently interrupt or change direction
- Complex voice workflows benefiting from configurable reasoning effort
- Multimodal applications combining live audio with text and image inputs
- Low-latency, natural speech-to-speech assistants
- Customer-service and call-center voice agents
- Voice agents requiring function calling and external tools
- Noisy environments where silence and background-noise handling matter
- Phone workflows requiring accurate recognition of names, numbers, codes, and other alphanumeric information
- Interactive applications where users frequently interrupt or change direction
- Complex voice workflows benefiting from configurable reasoning effort
- Multimodal applications combining live audio with text and image inputs
Quick Model Estimate
Your GPT Realtime 2.1 Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
📥 Input (1000 × $32.000000)
—
📤 Output (1000 × $64.000000)
—
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 | $32.0000 | $64.0000 | $0.4000 | 128,000 tokens | → |
| OpenAI | Image | Standard | $5.0000 | N/A | $0.5000 | 128,000 tokens | → |
| OpenAI | Text | Standard | $4.0000 | $24.0000 | $0.4000 | 128,000 tokens | → |
Other Models in the GPT Realtime 2.1 Family
FAQs about GPT Realtime 2.1
How much does GPT Realtime 2.1 cost per 1M tokens?
GPT Realtime 2.1 costs between $4.00 and $32.00 per million input tokens, and between $24.00 and $64.00 per million output tokens.
What does a typical workload cost with GPT Realtime 2.1?
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 Realtime 2.1 at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use GPT Realtime 2.1?
GPT Realtime 2.1 is available through OpenAI, from $4.00 per million input tokens.
What is GPT Realtime 2.1's context window?
GPT Realtime 2.1 has a context window of 128,000 tokens, and returns up to 32,000 tokens in a single response.