GPT-6 Luna (Reseller)
GPT-6 Luna for Codex (Responses API).
- Input price
- $0.01–$0.02list $0.10-90%
- Output price
- $0.05–$0.075list $0.50-90%
- Context
- 272K
- Max output
- 128K
- 30-day uptime
- —
- Released
- 2026-09-22
InputTextImageOutputText
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
All prices for this model, by service tier.
| Item | Standard | Flex | Batch | Priority | Price |
|---|---|---|---|---|---|
| Prompt ≤ 272K tokens | |||||
| Inputper 1M tokens | $0.01list $0.10-90% | $0.005list $0.05-90% | $0.005list $0.05-90% | $0.02list $0.20-90% | — |
| Outputper 1M tokens | $0.05list $0.50-90% | $0.025list $0.25-90% | $0.025list $0.25-90% | $0.10list $1.00-90% | — |
| Cache readper 1M tokens | $0.001list $0.01-90% | $0.0005list $0.005-90% | $0.0005list $0.005-90% | $0.002list $0.02-90% | — |
| Cache write (5 min)per 1M tokens | $0.0125list $0.125-90% | $0.006252list $0.0625-90% | $0.006252list $0.0625-90% | $0.025list $0.25-90% | — |
| Cache write (1 hour)per 1M tokens | $0.025list $0.25-90% | $0.0125list $0.125-90% | $0.0125list $0.125-90% | $0.05list $0.50-90% | — |
| Prompt > 272K tokens | |||||
| Inputper 1M tokens | $0.02list $0.20-90% | $0.01list $0.10-90% | $0.01list $0.10-90% | $0.04list $0.40-90% | — |
| Outputper 1M tokens | $0.075list $0.75-90% | $0.0375list $0.375-90% | $0.0375list $0.375-90% | $0.15list $1.50-90% | — |
| Cache readper 1M tokens | $0.002list $0.02-90% | $0.001list $0.01-90% | $0.001list $0.01-90% | $0.004list $0.04-90% | — |
| Cache write (5 min)per 1M tokens | $0.025list $0.25-90% | $0.0125list $0.125-90% | $0.0125list $0.125-90% | $0.05list $0.50-90% | — |
| Cache write (1 hour)per 1M tokens | $0.05list $0.50-90% | $0.025list $0.25-90% | $0.025list $0.25-90% | $0.10list $1.00-90% | — |
| Web searchper request | — | — | — | — | $0.001list $0.01-90% |
| Estimated cost of common use (500 output tokens each) | |||||
| One chat message3K input tokens | $0.00006 | $0.000032 | — | $0.000112 | — |
| Agent first turn100K tokens of context, none cached | $0.00128 | $0.000644 | — | $0.00255 | — |
| Each later agent turncontext read from cache, plus 2K new tokens | $0.000156 | $0.000084 | — | $0.000304 | — |
| 20-turn agent taskfirst turn plus 19 more | $0.00424 | $0.00224 | — | $0.00833 | — |
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.