Google Pro model for long-context analysis with published long-context price tiers after 200K input. Always estimate with your real prompt length in TokenCalculator.
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 | $1.25 |
| Output / 1M | $10.00 |
| Cached input / 1M | $0.125 |
| Batch input / 1M | $0.625 |
| Batch output / 1M | $5.00 |
| Long-context input (≥ 200K prompt) | $2.50 |
| Long-context output (≥ 200K prompt) | $15.00 |
| Long-context cached input (≥ 200K prompt) | $0.250 |
Model details
| Detail | Value |
|---|---|
| Provider | |
| Context window | 1M |
| Tokenizer | Approx (Gemini family) |
| Last verified | 2026-08-12 |
| API model id | gemini-2.5-pro |
Related tools
- Estimate API cost
- Count tokens
- Check context fit
- Estimate cache savings
- Compare batch pricing
- Compare tokenizers