Lowest GPT-6 list price for high volume chat, routing, and light coding. About half GPT-5.6 Luna. Prefer when Sol or Astra would overpay for simple turns.
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 | $0.100 |
| Output / 1M | $0.500 |
| Cached input / 1M | $0.010 |
| Cache write / 1M | $0.125 |
| Batch input / 1M | $0.050 |
| Batch output / 1M | $0.250 |
| Long-context input (≥ 272K prompt) | $0.200 |
| Long-context output (≥ 272K prompt) | $0.750 |
| Long-context cached input (≥ 272K prompt) | $0.020 |
Model details
| Detail | Value |
|---|---|
| Provider | OpenAI |
| Context window | 1.1M |
| Max output | 128K |
| Tokenizer | Exact (o200k_base) |
| Last verified | 2026-09-23 |
| API model id | gpt-6-luna |
Notes
Permanent standard rates. Prompts over 272K input tokens reprice the full request at the long-context band. Fast mode is 2× standard. Batch is 50% of standard.
More OpenAI models
Same provider catalog. Use these when you are comparing rates within one stack.
- GPT-4.1 Nano: $0.100 in / $0.400 out
- GPT-4o mini: $0.150 in / $0.600 out
- GPT-5 Nano: $0.050 in / $0.400 out
- GPT-5.6 Luna: $0.200 in / $1.20 out
- GPT-5 Mini: $0.250 in / $2.00 out
- GPT-4.1 Mini: $0.400 in / $1.60 out
- GPT-3.5 Turbo: $0.500 in / $1.50 out
- o1-mini: $1.10 in / $4.40 out
Featured comparisons
Browse the full set on Compare.
Related tools
- Estimate API cost
- Count tokens
- Check context fit
- Estimate cache savings
- Compare batch pricing
- Token visualizer
Related guides
- GPT-6 Luna pricing
- Luna vs Haiku
- GPT-6 Sol pricing
- GPT-6 272K pricing
- LLM API pricing
- Cost per token vs task