OpenAI

OpenAI provides GPT Image 2 for images and GPT text models for planning.

#Get a key

Create a key at platform.openai.com/api-keys and paste it into ⚙ Settings → OpenAI.

Like Gemini, image generation needs a billing-enabled account — a first-call 429 means billing, not a rate limit.

#Models

• gpt-image-2 — text-to-image (/images/generations) and image-to-image (/images/edits). Set the aspect ratio and quality on the node.

#What GPT Image 2 costs

GPT Image 2 is token-billed, so the real price depends on size × quality × aspect ratio. Brut ships a measured square-baseline table (from under a cent at 1K low up to ~$0.71 at 4K high) and shows the estimate before any paid run. Two things to know:

• Non-square is often much cheaper. OpenAI's token accounting can bill a 16:9 4K image at a fraction of a square 4K one (we've measured ~$0.15 vs ~$0.71 at high quality) — so treat the estimate as an upper ballpark when your aspect isn't square.
• The ledger holds the truth. Every run records the exact usage-priced amount OpenAI reported, never the estimate — check the spend panel for what a generation really billed.
• Text/planning — gpt-5.4-mini, gpt-5.5 for Refine and the cinema agents when you choose OpenAI as the planner.
• GPT-5.6 family — three text tiers with a reasoning dial: Sol ($4/M in · $20/M out — promotional through 2026-11-21, the deepest), Terra ($2/M in · $12/M out, balanced), Luna ($0.20/M in · $1.20/M out, cheap and fast — OpenAI cut it 80% in July 2026). Available everywhere text models are picked: Text → Text, the cinema agents, and Marcel's model lanes.

#The reasoning dial (GPT-5.6)

GPT-5.6 models can think before answering, and Brut exposes the dial: none · low · medium · high · xhigh (leave it on default to let OpenAI pick). Higher settings give deeper answers and cost more — reasoning tokens are billed as output tokens, so an xhigh answer can spend several times the tokens of the visible text. The dial appears on the Text → Text node, on each cinema agent (Scenarist, Artistic Director, DoP, Script Supervisor), and — for Marcel's brain lane — in ⚙ Settings; always only when the selected model actually supports it. Changing it re-plans (cache miss), like any input change.

#Native inpainting

OpenAI is the provider that applies an Inpaint mask natively — a true masked edit, where only the painted region changes and the rest is pixel-faithful. (Gemini treats the mask as strong guidance instead.) If precise local edits matter, inpaint on OpenAI.

#Notes

• Brut sends no temperature to the GPT-5-class planning models.
• Truncation is handled loudly: a finish_reason: length triggers one retry with more headroom, then a clear failure — never a silently cut-off plan.