Luma Photon production guide

Use this skill for the legacy-path Luma API image surface backed by photon-1 and photon-flash-1. Keep it separate from Ray video generation, newer UNI image workflows, Luma Agents, the consumer app, ComfyUI wrappers, and hosted third-party gateways. The string dream-machine remains in the documented Photon REST path even though Luma's current brand guidance calls that terminology retired.

All volatile facts below were verified against first-party sources on 2026-07-09. Recheck the API reference, billing dashboard, rate-limit page, and governing agreement immediately before production commitments.

Choose Photon deliberately

The documented image model IDs are:

• photon-1 — the default Photon model. Luma positions it for higher-fidelity generation.
• photon-flash-1 — the faster, lower-cost iteration model.

Treat those descriptions as provider positioning, not independent quality findings. Run a fixed brief-and-reference bake-off using the intended deliverable, then compare prompt adherence, source fidelity, text, anatomy, material continuity, latency, rejection rate, and actual account charge. Use Flash for broad exploration when it meets the bar; promote only finalists to Photon when measured quality justifies the cost.

Do not send Photon work to /generations/video, Ray models, Luma Agents, a consumer-session endpoint, or an OpenAI-compatible gateway. The first-party Photon create route is: