GPT-3.5 Turbo
cl100k_base
Structural tokenization analysis engine. Optimized for GPT-3.5 Turbo inputs. Calibrate context windows and compute precise API economics in real-time.
Context
4096
Type
LLM
Encoding
cl 100k base
CH44
WORD9
ENCODINGcl100k_base
// HAPPYTOKENIZER: WAITING FOR INPUT STREAM
Quick Answers
What is the GPT-3.5 Turbo token limit?
GPT-3.5 Turbo supports a 4,096 token context window. Paste your text above to see how much of that window your prompt fills.
What tokenizer does GPT-3.5 Turbo use?
GPT-3.5 Turbo uses the cl100k_base encoding (GPT-4 / GPT-3.5). This page counts tokens with the vendor's real vocabulary, so the numbers match what the API sees.
How much does GPT-3.5 Turbo cost per million tokens?
GPT-3.5 Turbo costs $0.50 per million input tokens and $1.50 per million output tokens, with cached input at $0.00 per million.
Model Insights
Modalities
InText
OutText
Supported Features
StreamingFunction Calling
Supported Endpoints
Chat Completions
Cost Manifest
Input / 1M$0.50
Output / 1M$1.50
Cached Write$0.00
* Rates are estimated based on OpenAI standard tier. Actual billing may vary based on batch processing and enterprise agreements.
// Technical Specifications
- ARCHITECTURE ID
- gpt-3.5-turbo
- TOKEN ENCODING
- cl100k_base
- MAX CONTEXT
- 4,096TOKENS