Use SpaceXAI Models in Big-AGI.

Running SpaceXAI in Big-AGI

Add your SpaceXAI API key and use Grok models at SpaceXAI's own API rates. Big-AGI isn't a reseller: no markup and no intermediary, so SpaceXAI bills you directly. SpaceXAI is the former xAI, now merged into SpaceX; the API and console still live at x.ai.

• Your key, your billing. Usage is billed by SpaceXAI directly, nothing routes through us.
• Reasoning effort. Grok's reasoning models take an effort setting, from none up to high, so you trade latency for depth on your terms.
• X Search, and more. Grok searches X directly with an adjustable recency window, plus general web search and a code sandbox, the only lab wired natively into X. New releases arrive tagged [new] with live pricing, no catalog wait.

Why not just Grok?

The Grok app is one model in one interface. Big-AGI runs Grok next to GPT, Claude, Gemini, and anything else you've connected, side by side in the same conversation, which the Grok app isn't built to do.

It also exposes what the app hides: reasoning effort and temperature are real parameters on SpaceXAI's reasoning models, set per request instead of the app's default. Your keys stay in your browser instead of a SpaceXAI account.

The billing model changes too: SpaceXAI charges per token, so a light user can spend less in a month than a subscription costs, and a heavy user never hits an artificial cap, just a bill for tokens used. Beam parallel runs do cost more, the honest tradeoff for comparing models side by side.

Your keys and your data

Turn on Direct Connection under SpaceXAI's Advanced settings and the browser calls SpaceXAI directly, bypassing the Big-AGI server, whenever your key is client-side and the API allows it. Your keys stay in your browser. Chats are stored locally first and sync only if you turn it on. The AI Inspector shows the exact request before it goes out: model, parameters, token counts, and a cost estimate.

SpaceXAI in Beam

Beam runs Grok against GPT, Claude, Gemini, or any other model you've connected, in parallel, then hands you Fusions: several strategies that combine, cross-check, and synthesize the parallel answers, which beats just picking the best one. Parallel runs use more tokens than a single chat.