Use DeepSeek Models in Big-AGI.

Running DeepSeek in Big-AGI

Add your DeepSeek API key and use DeepSeek's models at DeepSeek's own API rates. Big-AGI adds no markup and no intermediary: billing runs directly between you and DeepSeek, and your keys stay in your browser.

• Your key, your billing. Usage is billed by DeepSeek to your account. Big-AGI does not meter or charge for model usage.
• Reasoning, visible. Big-AGI renders DeepSeek's reasoning output in full, so you can follow how a model reached its answer, not just read the final line.
• Old models don't go stale. When DeepSeek retires a model, Big-AGI tracks the alias through to its successor and surfaces the retirement date, so you're never left calling a dead model.

Why not just the DeepSeek app?

The DeepSeek app is free and fine for a quick question, but it only ever shows you DeepSeek's answer. Beam sends the same prompt to DeepSeek and to GPT, Claude, or Gemini at once, so agreement or disagreement across labs becomes a signal you can act on, not a guess. You also get parameters the app hides (temperature, system prompt, per-turn model swaps), and your own key stays in your browser instead of sitting on DeepSeek's servers.

Your keys and your data

Turn on Direct Connection and the browser calls DeepSeek directly, bypassing the Big-AGI server, whenever your key is client-side and DeepSeek allows it. Your keys stay in your browser. Chats are stored locally first and sync only if you turn it on. The AI Inspector opens on any message to show the exact request sent to DeepSeek, the token counts, and a cost estimate for that call.

DeepSeek in Beam

Run DeepSeek in parallel with GPT, Claude, and Gemini on the same prompt, then reach for Fusions: several strategies that combine, cross-check, and synthesize the parallel answers, which beats just picking the single best one. Parallel runs use more tokens than a single chat.