Direct keys or aggregators? — choosing your access path

Brut is bring-your-own-key at heart: the cheapest, highest-fidelity way to run it is a handful of native provider keys, and nothing Brut does ever adds a markup to them. But not everyone wants to open four provider consoles — so Brut also speaks to aggregators, as routes: your aggregator credential serves models you have no native key for, visibly, at the aggregator's own prices. This page is the honest comparison.

#The trade-off in one table

Whatever you pick, routing is never silent: routed nodes show ⇄ runs via …, the paid-run confirm says who bills, and the spend ledger records it per generation.

#How much of Brut works with what

¹ Nano Banana Pro / 2 / original — everywhere images are made: Text→Image, Image→Image, Compose, Multi-Shot tiles, storyboard keyframes. ² Refine, the Multi-Shot planner, the cinema crew, Text→Text — all 13 text models; planning routes through OpenRouter only (fal's router took no images and refuses the newer reasoning models — dropped 2026-07-26). "Free & local" = Sequence, Conform, the boards, the library, Storyboard editing.

#Which path should you pick?

Three setups cover almost everyone. Pick by what you care about most:

#1. Native keys — pick this if you care about price and control

Gemini + OpenAI + one video provider (+ Anthropic for Marcel's best brain). This is what Brut is built around, and it wins on every axis except setup time:

• Cheapest per generation, structurally. You pay each provider's list rate, full stop — no reseller margin, no credit fee. At studio volume (hundreds of images, dozens of clips a week) the difference is real money.
• Every knob of every model: exact inpaint masks (OpenAI), Kling's 4K master tier, Seedance Smart Length, native 4K rates — none of which any aggregator carries.
• The cost: ~5 minutes per provider console, each with billing enabled.

#2. One OpenRouter key — pick this if you care about simplicity

The 2-minute setup, and since v1.0.8 it's a genuinely complete studio: images with Brut's own size/aspect menus, the whole video set (Kling std/pro, Veo 3.1/Fast/Lite with end frames, Seedance), every planning model, and Marcel — chat, ambient narration and acting, with Anthropic prompt caching passing through so long conversations cost the same as on a native key. A unique honesty bonus: OpenRouter reports the exact billed cost of every job, and Brut writes it straight onto your ledger.

What you give up: GPT Image 2 sizing (quality knob only), Kling 4K, Smart Length, exact inpaint masks (approximate ones work), and the upscalers. Prices are pass-through list rates for text and images; video carries a modest margin.

#3. OpenRouter + fal.ai — pick this if you want aggregator simplicity at better video rates

Two keys instead of one, and the route table quietly picks the better door per model: OpenRouter keeps text, Marcel, and images (its native-menu fidelity wins there); fal takes over video — its Kling rates run noticeably cheaper — and adds GPT Image 2 sizing via its own presets. This is the setup we'd suggest to most people who don't want provider consoles: one evening of video work typically pays for the second key's two minutes of setup.

#The pattern to remember

Keys you add later always take over their models automatically. Start with OpenRouter today, add fal when video volume grows, add native keys whenever one provider starts costing real money — nothing to reconfigure, the routes just step aside.

Also supported, for narrower cases: a Higgsfield subscription (no key at all — Nano Banana 2 + Seedance billed to plan credits; no planning, no Marcel) and a Replicate token (a redundancy door covering roughly what fal covers, incl. Veo end frames). Both work, neither is where we'd start.