How does GPT tokenization work?

GPT models use Byte Pair Encoding (BPE) tokenization via the tiktoken library. Common words are single tokens; rare words split into subword pieces. This tool uses a word-based approximation (~1.3 tokens per word).

What is the GPT-4o context window?

GPT-4o and GPT-4o mini both support a 128,000-token context window, equivalent to roughly 96,000 words or about 200 pages of text.

How is GPT-4o pricing calculated?

GPT-4o charges $2.50 per million input tokens and $10.00 per million output tokens. GPT-4o mini is much cheaper at $0.15 per million input and $0.60 per million output.

Is my text sent to OpenAI?

No. Token counting happens entirely in your browser. No text is sent to any server.

OpenAI Token Counter

Count tokens for GPT-4o, GPT-4 Turbo, and GPT-3.5 models.

Model

Text input

Tokens0

Words0

Characters0

Context window usage

00.0% of 128.0K

Cost estimate

Per request$0.000000

Per 1K requests$0.000000

Daily (100 req)$0.000000

Monthly est.$0.000000

0 input tokens0 output tokens

Related Tools

TKNAI Token CounterNEW

Count tokens for GPT, Claude, Gemini, and LLaMA models.

CLTClaude Token CounterNEW

Count tokens for Claude 3.5 Sonnet, Opus, and Haiku models.

GPTOpenAI API Cost CalculatorNEW

Calculate GPT-4o, GPT-4 Turbo, and GPT-3.5 API costs.

OABOpenAI Request BuilderNEW

Build OpenAI Chat Completions API request payloads and cURL commands.

Learn More

guide:token counting guide:openai vs claude

FAQ

How does GPT tokenization work?: GPT models use Byte Pair Encoding (BPE) tokenization via the tiktoken library. Common words are single tokens; rare words split into subword pieces. This tool uses a word-based approximation (~1.3 tokens per word).
What is the GPT-4o context window?: GPT-4o and GPT-4o mini both support a 128,000-token context window, equivalent to roughly 96,000 words or about 200 pages of text.
How is GPT-4o pricing calculated?: GPT-4o charges $2.50 per million input tokens and $10.00 per million output tokens. GPT-4o mini is much cheaper at $0.15 per million input and $0.60 per million output.
Is my text sent to OpenAI?: No. Token counting happens entirely in your browser. No text is sent to any server.

Count tokens for OpenAI GPT models including GPT-4o, GPT-4o mini, GPT-4 Turbo, and GPT-3.5 Turbo. See context window usage and per-request cost estimate. Uses word-based heuristics — results are approximate.