OpenAI logo

GPT-4o Realtime


GPT-4o Realtime is OpenAI logoOpenAI's language model with a 128K context window and up to 4K output tokens. A real-time variant of GPT-4o capable of responding to audio and text inputs with low latency over WebRTC or WebSocket interfaces.
Spec
Canonical IDopenai-gpt-4o-realtime
TypeLanguage
StatusActive
CreatorOpenAIOpenAI
Providers
Context Window128K tokens
Max Output4K tokens
Input ModalitiesAudioText
Output ModalitiesAudioText
Release Date · 2 years ago
Knowledge Cutoff
Time to First Token
0.00s
#111
Output TPS
0.0
#321

Capabilities

Input2/5
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
OpenAI logo
OpenAI
gpt-4o-realtime-preview
$5.00$20.00$2.50$40.00$80.00

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GPT-5.4 Mini1.1M$0.750$4.50Available
GPT-5.4 Nano1.1M$0.200$1.25Available
GPT-5.41.1M$2.50$15.00Available
GPT-5.4 Pro1.1M$30.00$180.00Available
GPT-5.4 3.51.1MAvailable
GPT-5.4 Pro 3.51.1MAvailable
GPT-5.3 Chat128K$1.75$14.00Available
GPT-5.3 Codex400K$1.75$14.00Available
GPT-5.3 Codex Spark128KAvailable
GPT-5.3 Instant128KAvailable
GPT-4o Realtime128KCurrent

Model IDs