GPT-4o Realtime Preview
o200k_base
Structural tokenization analysis engine. Optimized for GPT-4o Realtime Preview inputs. Calibrate context windows and compute precise API economics in real-time.
Context
128k
Type
LLM
Encoding
o 200k base
CH44
WORD9
ENCODINGo200k_base
// HAPPYTOKENIZER: WAITING FOR INPUT STREAM
Quick Answers
What is the GPT-4o Realtime Preview token limit?
GPT-4o Realtime Preview supports a 128,000 token context window. Paste your text above to see how much of that window your prompt fills.
What tokenizer does GPT-4o Realtime Preview use?
GPT-4o Realtime Preview uses OpenAI's o200k_base encoding. This page counts tokens with the vendor's real vocabulary, so the numbers match what the API sees.
How much does GPT-4o Realtime Preview cost per million tokens?
GPT-4o Realtime Preview costs $5.00 per million input tokens and $20.00 per million output tokens, with cached input at $2.50 per million.
Model Insights
Modalities
InTextImage
OutText
Supported Features
StreamingStructured OutputsFunction CallingWeb SearchPrompt CachingReasoning Tokens
Supported Endpoints
ResponsesBatch
Cost Manifest
Input / 1M$5.00
Output / 1M$20.00
Cached Write$2.50
* Rates are estimated based on OpenAI standard tier. Actual billing may vary based on batch processing and enterprise agreements.
// Technical Specifications
- ARCHITECTURE ID
- gpt-4o-realtime-preview
- TOKEN ENCODING
- o200k_base
- MAX CONTEXT
- 128,000TOKENS