Claude Token Counter

Most token counters only estimate Claude tokens, because Anthropic’s tokenizer isn’t public. This one asks Anthropic’s official token counting API, so the number matches what you’ll be billed for.

0GPT tokens
0Claude tokens
0words
0characters
ModelTokensPrice / 1M in · outEst. cost
Claude Fable 5.2Anthropic0exact$8 · $40$0
Claude Opus 5.5Anthropic0exact$4 · $20$0
Claude Sonnet 5.5Anthropic0exact$2 · $10$0
Claude Haiku 5.5Anthropic0exact$0.10 · $0.50$0.50 / $2.50 above 100K-token prompts$0
GPT-6.1 SolOpenAI0estimate$2 · $10$4 / $15 above 272K-token prompts$0
GPT-6.1 TerraOpenAI0estimate$1 · $5$2 / $7.50 above 272K-token prompts$0
GPT-6 AstraOpenAI0estimate$10 · $50$20 / $75 above 272K-token prompts$0
GPT-6 LunaOpenAI0estimate$0.10 · $0.50$0.20 / $0.75 above 272K-token prompts$0
GPT-5.6 SolOpenAI0exact$4 · $20Promotional pricing until Nov 30, 2026 · $8 / $30 above 272K$0
GPT-5.5OpenAI0exact$5 · $30$10 / $45 above 272K-token prompts$0
GPT-5.4 miniOpenAI0exact$0.75 · $4.50$0
Gemini 4 CarbonGoogle0estimate$2 · $10$4 · $20 from Dec 1, 2026$0
Gemini 4 ArgonGoogle0estimate$2 · $10$4 · $20 from Dec 1, 2026$0
Gemini 4 HydrogenGoogle0estimate$1.50 · $7.50$0
Gemini 3.8 FlashGoogle0estimate$0.75 · $3.75$1.50 · $7.50 from Jan 1, 2027$0
Gemini 3.1 Pro (preview)Google0estimate$2 · $12$4 / $18 above 200K-token prompts$0
Gemini 3.1 Flash-LiteGoogle0estimate$0.25 · $1.50$0

Prices per 1M tokens, standard tier, last checked 2026-11-17. Estimated cost = input tokens × input price + output tokens × output price, times the number of requests. Exact = the provider’s own tokenizer; estimate = the provider hasn’t published its tokenizer, so the count is approximated.

Frequently asked questions

Why can’t I use tiktoken to count Claude tokens?

tiktoken is OpenAI’s tokenizer. Claude uses a different one, and tiktoken typically undercounts Claude tokens by 15–20% on English text, and by more on code or other languages.

Do all Claude models count tokens the same way?

No. Newer Claude models use a newer tokenizer that can produce up to ~35% more tokens than older ones for the same text, which is why we count each model separately.

Is my text stored?

No. OpenAI token counts are calculated entirely in your browser. For exact Claude counts, your text is sent to Anthropic’s token counting API and the result is returned to you. We do not log or store the text.

Why do different models give different token counts for the same text?

Each provider uses its own tokenizer — the rules that split text into tokens. The same sentence can be 100 tokens for GPT and 115 for Claude. Code, non-English text and emoji usually differ the most.

Related tools