A browser extension by SpacePrompts that counts tokens and estimates costs for your AI prompts right from your browser.
- Count tokens for GPT-5.4, Claude Sonnet 4.6, Gemini 3.1 Pro Preview, DeepSeek V3.2, Qwen 3.5, and Llama 4 Maverick
- Estimated input cost per model
- Character count
- Real-time results as you type
| Model | Provider | Input Price |
|---|---|---|
| GPT-5.4 | OpenAI | $2.50 / 1M tokens |
| Claude Sonnet 4.6 | Anthropic | $3.00 / 1M tokens |
| Gemini 3.1 Pro Preview | $2.00 / 1M tokens (≤200K), $4.00 / 1M tokens (>200K) | |
| DeepSeek V3.2 | DeepSeek | $0.28 / 1M tokens |
| Qwen 3.5 | Alibaba | $0.40 / 1M tokens |
| Llama 4 Maverick | Meta | $0.19 / 1M tokens |
- Node.js
- pnpm
pnpm installCopy the example env file and fill in your values:
cp .env.example .env.localpnpm devpnpm build| Variable | Description |
|---|---|
WXT_MANIFEST_KEY |
Chrome extension manifest key (optional, for dev) |
WXT_API_URL |
Tokenizer API endpoint |
WXT_EXTENSION_KEY |
API key sent via X-Extension-Key header |
The tokenizer API is rate limited to 60 requests per minute per IP address. Requests exceeding this limit will receive a 429 Too Many Requests response.
Token counting is powered by the following open source libraries:
- tiktoken — OpenAI's tokenizer for GPT models
- HuggingFace Tokenizers — used for Claude, Gemini, DeepSeek, Qwen, and Llama models
Found a bug or have a suggestion? Open an issue.
MIT