Release and model choices
The broader release includes paying developers through Google AI Studio and Gemini for business, with rollout to Google AI Ultra subscribers across supported products. Check Google's current availability rather than treating the earlier restricted release as public access.
Carbon is positioned for tasks such as architectural redesign, multi-package migrations, dense document synthesis and extended verification. A long-running agent can accumulate tool results and context across many calls, so the initial prompt alone cannot predict the task bill.
| Model | Local counting | Open tool |
|---|---|---|
| Gemini 4 Carbon | Local estimate | Select Gemini 4 Carbon |
How to count Gemini 4 Carbon tokens
Text planning rule: characters ÷ 4, rounded up. This is the provider's general English-oriented planning guidance, not a published Gemini 4 Carbon tokenizer. Other languages, code, emoji and punctuation can differ substantially. The estimate does not produce model token IDs or guarantee a context or billing limit.
Paste text into Plain text mode, or use Chat messages to count each message body independently. Switching models preserves your input. Chat mode excludes role names, separators and provider wrappers; adding bodies does not reproduce a serialized API conversation.
Local processing does not send your prompt to a model API or generate a response. Published tokenizer assets may be loaded by the browser, while the text analysis itself runs on your device.
Request limits and usage
Carbon may spend more tokens exploring and checking a difficult problem. This tool estimates only the pasted text or individual message bodies, excluding generated reasoning, outputs and other execution steps.
For a production request, include the actual conversation, system instructions, tool schemas and supported media in the provider's counting workflow when available. Check response usage after generation and account for subsequent calls, cache behavior, reasoning and output separately.
- A model's advertised context window is not a guaranteed amount of pasted text.
- A faster model or a cheaper token rate does not establish a lower total bill for every task.
- Recheck the exact model version and counting method when migrating an existing prompt.
Tiktokenizer Reference Sources
Tokenizer behavior and model limits change. Verify production decisions with current provider documentation: