OpenAI: GPT Realtime 2.1

openai/gpt-realtime-2.1

GPT Realtime 2.1: speech-to-speech over WebSocket (GET /v1/realtime), billed per modality token.

Model specifications

Input
text, audio
Output
text, audio
Context
10,000 tokens
Input price
$4 / 1M tokens
Output price
$24 / 1M tokens
Released
2026-11-17

Capabilities

  • Streaming

Provider pricing, discounts and data privacy

Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.

Standard service tier

1 available provider · tier input average $4 / 1M tokens · tier output average $24 / 1M tokens

OpenAI

Tier: Standard · Region: US

Pricing
Input
$4 / 1M tokens
Output
$24 / 1M tokens
Cache read
$0.4 / 1M tokens
Audio input
$32

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
No
Data retention
Zero retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
Yes
HIPAA compliant
Yes
SOC 2 certified
Yes
BYOK supported
Yes

Frequently asked questions

What is OpenAI: GPT Realtime 2.1?
GPT Realtime 2.1: speech-to-speech over WebSocket (GET /v1/realtime), billed per modality token.
How much does OpenAI: GPT Realtime 2.1 cost?
Input costs start at $4 / 1M tokens and output costs start at $24 / 1M tokens. Provider-level prices vary by service tier.
What is the context length of OpenAI: GPT Realtime 2.1?
OpenAI: GPT Realtime 2.1 supports a 10,000 token context window.
What capabilities does OpenAI: GPT Realtime 2.1 support?
OpenAI: GPT Realtime 2.1 supports Streaming.
Which providers offer OpenAI: GPT Realtime 2.1?
OpenAI: GPT Realtime 2.1 is available from OpenAI.
How do providers handle data privacy for OpenAI: GPT Realtime 2.1?
1 of 1 providers report that customer data is not used for training, and 0 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.

Browse all AI models