GPT-6 Luna
- Input
- $0.20
- Cached input
- $0.02
- Cache write · 30 min
- $0.25
- Cache write · 12 h
- $0.50
- Output
- $1.00
How usage is measured
Your company’s AI usage
Your allowance is measured at SynthCrew service rates, not as provider credits. Each request keeps the rate version selected before it starts. Routes through OpenRouter include funding overhead in their usage rate; there is no second top-up fee on the request.
Clear model rates.
USD per million tokens · standard processing
| Model | Input | Cached input | Cache write · 30 min | Cache write · 12 h | Output |
|---|---|---|---|---|---|
| GPT-6 Luna | $0.20 | $0.02 | $0.25 | $0.50 | $1.00 |
| GPT-6.1 Terra | $2.00 | $0.10 | $2.50 | $5.00 | $10.00 |
| GPT-6.1 Sol | $4.00 | $0.20 | $5.00 | $10.00 | $20.00 |
| GPT-6 Astra | $20.00 | $2.00 | $25.00 | $50.00 | $100.00 |
GPT-6.1 Terra
- Input
- $2.00
- Cached input
- $0.10
- Cache write · 30 min
- $2.50
- Cache write · 12 h
- $5.00
- Output
- $10.00
GPT-6.1 Sol
- Input
- $4.00
- Cached input
- $0.20
- Cache write · 30 min
- $5.00
- Cache write · 12 h
- $10.00
- Output
- $20.00
GPT-6 Astra
- Input
- $20.00
- Cached input
- $2.00
- Cache write · 30 min
- $25.00
- Cache write · 12 h
- $50.00
- Output
- $100.00
Rates dated November 4, 2026. Above 272,000 input tokens, input/cache rates are 2× and output is 1.5×. Reasoning is included in output. Applicable taxes are extra.
How usage is measured →