Balanced Claude for most production apps: strong quality without Opus or Fable cost. Best default when you need speed and intelligence together.
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 | $10.00 |
| Cached input / 1M | $0.200 |
| Cache write / 1M | $2.50 |
| Batch input / 1M | $1.00 |
| Batch output / 1M | $5.00 |
Model details
| Detail | Value |
|---|---|
| Provider | Anthropic |
| Context window | 1M |
| Max output | 128K |
| Tokenizer | Approx (Anthropic family) |
| Last verified | 2026-09-17 |
| API model id | claude-sonnet-5 |
Notes
Introductory $2/$10 rates are now the permanent standard. The previously planned Sep 2026 rise to $3/$15 did not take effect.
Related tools
- Estimate API cost
- Count tokens
- Check context fit
- Estimate cache savings
- Compare batch pricing
- Compare vs GPT tokenizer