Newer Gemini Pro preview with higher list rates and long-context tiers. Confirm the preview model id and re-verify pricing before production lock-in.
Privacy first counting
TokenCalculator counts tokens in your browser when an Exact encoding is available. Prompt text does not need to leave your device for local counting.
Pricing snapshot
USD per 1 million tokens. Verify against the provider source before you lock budget.
| Rate | USD |
|---|---|
| Input / 1M | $2.00 |
| Output / 1M | $12.00 |
| Cached input / 1M | $0.200 |
| Batch input / 1M | $1.00 |
| Batch output / 1M | $6.00 |
| Long-context input (≥ 200K prompt) | $4.00 |
| Long-context output (≥ 200K prompt) | $18.00 |
Model details
| Detail | Value |
|---|---|
| Provider | |
| Context window | 1M |
| Tokenizer | Approx (Gemini family) |
| Last verified | 2026-08-12 |
| API model id | gemini-3.1-pro-preview |
Notes
Preview model id may change; confirm on Google pricing docs.
Related tools
- Estimate API cost
- Count tokens
- Check context fit
- Estimate cache savings
- Compare batch pricing
- Compare tokenizers