Gemini Token Counter
Estimate how many tokens your text uses on Gemini and what it will cost, next to GPT and Claude so you can compare. Gemini counts are estimates because Google doesn’t publish a browser tokenizer.
- ✓ Prices checked Nov 17, 2026
- ✓ Exact Claude counts via Anthropic’s API
- ✓ Exact GPT-5 counts
- ✓ No signup
| Model | Tokens | Est. cost |
|---|---|---|
| Gemini 4 CarbonGoogle | 0estimate | $0 |
| Gemini 4 ArgonGoogle | 0estimate | $0 |
| Gemini 4 HydrogenGoogle | 0estimate | $0 |
| Gemini 3.8 FlashGoogle | 0estimate | $0 |
| Gemini 3.1 Pro (preview)Google | 0estimate | $0 |
| Gemini 3.1 Flash-LiteGoogle | 0estimate | $0 |
| Claude Fable 5.2Anthropic | 0exact | $0 |
| Claude Opus 5.5Anthropic | 0exact | $0 |
| Claude Sonnet 5.5Anthropic | 0exact | $0 |
| Claude Haiku 5.5Anthropic | 0exact | $0 |
| GPT-6.1 SolOpenAI | 0estimate | $0 |
| GPT-6.1 TerraOpenAI | 0estimate | $0 |
| GPT-6 AstraOpenAI | 0estimate | $0 |
| GPT-6 LunaOpenAI | 0estimate | $0 |
| GPT-5.6 SolOpenAI | 0exact | $0 |
| GPT-5.5OpenAI | 0exact | $0 |
| GPT-5.4 miniOpenAI | 0exact | $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
How accurate is the Gemini count?
It is an estimate based on GPT’s tokenizer, which is usually within a few percent of Gemini’s for English text. For billing-grade numbers, use the countTokens method in Google’s Gemini API.
Are Gemini prices going up?
Yes. Google has announced that Gemini 4 Carbon and Argon double to $4 input / $20 output per 1M tokens on December 1, 2026, and Gemini 3.8 Flash doubles to $1.50 / $7.50 on January 1, 2027. The calculator switches to the new price automatically on those dates.
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.