Entry reasoning tier for lighter hard tasks. Useful when you want reasoning behavior without o3 spend. Still verify output-heavy prompts in the calculator.
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 | $1.10 |
| Output / 1M | $4.40 |
| Cached input / 1M | $0.550 |
| Batch input / 1M | $0.550 |
| Batch output / 1M | $2.20 |
Model details
| Detail | Value |
|---|---|
| Provider | OpenAI |
| Context window | 200K |
| Tokenizer | Exact (o200k_base) |
| Last verified | 2026-08-12 |
| API model id | o3-mini |
Notes
Budget reasoning; reasoning tokens billed as output.
Related tools
- Estimate API cost
- Count tokens
- Check context fit
- Estimate cache savings
- Compare batch pricing
- Token visualizer
Related guides
- LLM API pricing
- Exact vs Approx
- OpenAI token calculator
- o200k vs cl100k: which OpenAI encoding counts your text?