GPT-5.6 Luna
gpt-5.6-luna
Multimodal
7 gateways
1.87x price spread
Where you can run it
| Gateway | Its id | Context | Max output | Input / Mtok | Output / Mtok |
|---|---|---|---|---|---|
| Cheaper Inference Cheapest input | gpt-5.6-luna |
1.1M | 128K | $0.107 | $0.641 |
| Concentrate | gpt-5.6-luna |
1.1M | 128K | — | — |
| Experiential Labs | gpt-5.6-luna |
1.1M | 128K | $0.200 | $1.20 |
| LLM Gateway | gpt-5.6-luna |
1.1M | — | $0.200 | $1.20 |
| OrcaRouter | gpt-5.6-luna |
1.1M | 128K | $0.200 | $1.20 |
| Ramp Router | gpt-5.6-luna |
1.1M | 128K | $0.200 | $1.20 |
| SayGM | gpt-5.6-luna |
— | — | $0.124 | $0.742 |
Prices are US dollars per million tokens, as published in each gateway's own catalog at the last crawl. A dash means that gateway publishes no value — not that it is free. Rows differ because gateways set their own markup, and some let you bring your own provider key.
- Canonical id
gpt-5.6-luna- Vendor
- OpenAI
- Type
- Multimodal
- Gateways serving it
- Cheaper InferenceConcentrateExperiential LabsLLM GatewayOrcaRouterRampSayGM
- Largest context window
- 1.1M tokens
- Input price range
- $0.107 – $0.200 / Mtok
- Price spread
- 1.87x between cheapest and dearest gateway
- Accepts
- Text, Image
- Returns
- Text
- Cataloged since
History
What changed for GPT-5.6 Luna
Recorded by the daily catalog crawl — when gateways picked this model up, dropped it, or repriced it.
- Cheaper Inference raised input 13.7% to $0.107 and output 13.7% to $0.641 on gpt-5.6-luna
- Cheaper Inference cut input 43.2% to $0.094 and output 43.2% to $0.564 on gpt-5.6-luna
- SayGM raised input 2.4% to $0.124 and output 2.4% to $0.742 on GPT-5.6 Luna
- Cheaper Inference raised input 51.3% to $0.165 and output 51.3% to $0.991 on gpt-5.6-luna