Use Cerebras Models in Big-AGI.

Running Cerebras in Big-AGI

Add your Cerebras API key and run open models on Cerebras wafer-scale hardware at their own API rates. Big-AGI adds no markup and no intermediary: the billing relationship runs directly between you and Cerebras.

• Your key, your billing. Usage is billed by Cerebras to your account.
• Accurate toggles, even when Cerebras' catalog isn't. Cerebras' own public catalog sometimes under-reports what a model can do; Big-AGI's editorial data wins for known models, so vision, tools, and reasoning toggles stay correct regardless.
• Built for speed. Cerebras serves open models at very high tokens per second, so long generations and agentic loops feel instant.

Why Big-AGI instead of the playground?

Cerebras' playground proves the speed; it doesn't give you a workspace. Big-AGI adds persistent chats, personas, and attachments on top of the raw API, then puts that speed to work in Beam: run a Cerebras model next to Claude, GPT, and Gemini, and it's usually done before the others have finished a sentence, so running several models in parallel feels instant instead of like a wait. Parameters, the key, and the chats stay yours to control.

Your keys and your data

Turn on Direct Connection and the browser calls Cerebras directly, bypassing the Big-AGI server, when your key is client-side and Cerebras 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, the token counts, and a cost estimate.

Cerebras in Beam

Put a Cerebras model into a Beam next to Claude, GPT, and Gemini, and it's usually the first one finished. Fusions then combine, cross-check, and synthesize the parallel answers instead of just picking the best one. Parallel runs use more tokens than a single chat.