GPT-5.6 Luna
A cost-efficient GPT-5.6 model optimized for high-volume reasoning and tool-use workloads.
- Input price
- $0.18–$0.36list $0.2010% off
- Output price
- $1.08–$1.62list $1.2010% off
- Context
- 1.1M
- Max output
- 128K
- Capability
- 157 (#34 of 82)
- Human preference
- 1431
- 30-day uptime
- —
- Released
- 2026-07-09
- Knowledge cutoff
- 2026-02-16
Providers
This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].
- SuccessTTFT
- Azure AI FoundryGlobal——
- OpenAIUnited States——
Pricing
Prices for this model. Each request is billed at these prices, whichever provider serves it.
| Item | Standard | Standard Discount | Flex | Flex Discount | Batch | Batch Discount | Price | Price Discount | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Prompt ≤ 272K tokens | ||||||||||||
| Inputper 1M tokens | $0.18 | list $0.20 | 10% off | $0.09 | list $0.10 | 10% off | $0.09 | list $0.10 | 10% off | — | ||
| Outputper 1M tokens | $1.08 | list $1.20 | 10% off | $0.54 | list $0.60 | 10% off | $0.54 | list $0.60 | 10% off | — | ||
| Cache readper 1M tokens | $0.018 | list $0.02 | 10% off | $0.009 | list $0.01 | 10% off | $0.009 | list $0.01 | 10% off | — | ||
| Cache write (5 min)per 1M tokens | $0.225 | list $0.25 | 10% off | $0.1125 | list $0.125 | 10% off | $0.1125 | list $0.125 | 10% off | — | ||
| Prompt > 272K tokens | ||||||||||||
| Inputper 1M tokens | $0.36 | list $0.40 | 10% off | $0.18 | list $0.20 | 10% off | $0.18 | list $0.20 | 10% off | — | ||
| Outputper 1M tokens | $1.62 | list $1.80 | 10% off | $0.81 | list $0.90 | 10% off | $0.81 | list $0.90 | 10% off | — | ||
| Cache readper 1M tokens | $0.036 | list $0.04 | 10% off | $0.018 | list $0.02 | 10% off | $0.018 | list $0.02 | 10% off | — | ||
| Cache write (5 min)per 1M tokens | $0.45 | list $0.50 | 10% off | $0.225 | list $0.25 | 10% off | $0.225 | list $0.25 | 10% off | — | ||
| Web searchper request | — | — | — | $0.0126 | list $0.014 | 10% off | ||||||
| Estimated cost of common use (500 output tokens each) | ||||||||||||
| One chat message3K input tokens | $0.00108 | $0.000544 | — | — | ||||||||
| Agent first turn100K tokens of context, none cached | $0.023 | $0.0115 | — | — | ||||||||
| Each later agent turncontext read from cache, plus 2K new tokens | $0.00279 | $0.0014 | — | — | ||||||||
| 20-turn agent taskfirst turn plus 19 more | $0.0761 | $0.0381 | — | — | ||||||||
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.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text