OpenAI logo

GPT Realtime


GPT Realtime is OpenAI's language model with a 32K context window and up to 4K output tokens, available from 2 providers, starting at $4.00 / 1M input and $16.00 / 1M output. A general-availability realtime LLM capable of responding to audio and text inputs over WebRTC, WebSocket, or SIP connections with low latency.
Specifications
Canonical IDopenai-gpt-realtime
TypeLanguage
StatusActive
CreatorOpenAIOpenAI
Providers
Context Window32K tokens
Max Output4K tokens
Input ModalitiesAudioImageText
Output ModalitiesAudioText
Release Date · 9 months ago
Knowledge Cutoff

Capabilities

Input3/5
Text
Image
Audio
Video·
PDF·
Output2/5
Text
Image·
Audio
Video·
Embedding·
Capabilities2/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Audio In
$ / 1M
Audio Out
$ / 1M
Azure AI Foundry logo
Azure AI Foundry
azure/gpt-realtime-2025-08-28
$4.00$16.00$4.00$32.00$64.00
OpenAI logo
OpenAI
gpt-realtime
$4.00$16.00$0.400$32.00$64.00

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GPT-5 Mini Image400K$2.50$2.00Available
GPT-5 Image400K$10.00$10.00Available
GPT-5 Pro400K$15.00$120.00Available
GPT-5 Codex400K$1.25$10.00Available
GPT-5410K$1.25$10.00Available
GPT-5 Chat128K$1.25$10.00Available
GPT-5 Mini400K$0.250$2.00Available
GPT-5 Nano400K$0.050$0.400Available
GPT-5 ChatGPTAvailable
GPT-5 LowAvailable
GPT Realtime32K$4.00$16.00Current

Model IDs