What is Claude's context window?

All Claude 3 models support a 200,000-token context window — one of the largest available. This equates to roughly 150,000 words or about 500 pages of text.

How does Claude tokenization differ from GPT?

Claude uses its own tokenizer, which tends to produce slightly more tokens per word (~1.35) compared to GPT's tiktoken (~1.3). Code and special characters may also tokenize differently.

How is Claude pricing calculated?

Claude 3.5 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens. Claude 3 Haiku is much cheaper at $0.25 per million input and $1.25 per million output.

Is my text sent to Anthropic?

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

Claude Token Counter

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

Model

Text input

Tokens0

Words0

Characters0

Context window usage

00.0% of 200.0K

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.

GPTOpenAI Token CounterNEW

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

CLDClaude API Cost CalculatorNEW

Calculate Anthropic Claude API costs for Sonnet, Opus, and Haiku.

CABClaude API Request BuilderNEW

Build Anthropic Messages API request payloads and cURL commands.

Learn More

guide:token counting guide:claude system prompts

FAQ

What is Claude's context window?: All Claude 3 models support a 200,000-token context window — one of the largest available. This equates to roughly 150,000 words or about 500 pages of text.
How does Claude tokenization differ from GPT?: Claude uses its own tokenizer, which tends to produce slightly more tokens per word (~1.35) compared to GPT's tiktoken (~1.3). Code and special characters may also tokenize differently.
How is Claude pricing calculated?: Claude 3.5 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens. Claude 3 Haiku is much cheaper at $0.25 per million input and $1.25 per million output.
Is my text sent to Anthropic?: No. Token counting happens entirely in your browser. No text is sent to any server.

Count tokens for Anthropic Claude models including Claude 3.5 Sonnet, Claude 3 Opus, and Claude 3 Haiku. See the 200K context window usage and per-request cost estimate. Uses word-based heuristics — results are approximate.