Default GPT-5.6 tier for everyday production. Cheaper than Sol, stronger than Luna. Exact OpenAI counts 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 | $2.00 |
| Output / 1M | $12.00 |
| Cached input / 1M | $0.200 |
| Cache write / 1M | $2.50 |
| Batch input / 1M | $1.00 |
| Batch output / 1M | $6.00 |
| Long-context input (≥ 272K prompt) | $4.00 |
| Long-context output (≥ 272K prompt) | $18.00 |
| Long-context cached input (≥ 272K prompt) | $0.400 |
Model details
| Detail | Value |
|---|---|
| Provider | OpenAI |
| Context window | 1.1M |
| Tokenizer | Exact (o200k_base) |
| Last verified | 2026-09-18 |
| API model id | gpt-5.6-terra |
More OpenAI models
Same provider catalog. Use these when you are comparing rates within one stack.
- GPT-4.1: $2.00 in / $8.00 out
- GPT-4.1 (2025-04-14): $2.00 in / $8.00 out
- o3: $2.00 in / $8.00 out
- GPT-4o: $2.50 in / $10.00 out
- GPT-4o (2024-08-06): $2.50 in / $10.00 out
- GPT-5: $1.25 in / $10.00 out
- o1-mini: $1.10 in / $4.40 out
- o3-mini: $1.10 in / $4.40 out
Related tools
- Estimate API cost
- Count tokens
- Check context fit
- Estimate cache savings
- Compare batch pricing
- Token visualizer