Models
Skynet puts every major model behind one subscription: GPT, Claude, Gemini, DeepSeek, Perplexity, and Groq-hosted models today, plus whatever launches next. You stop thinking about which model to use; you describe the work, and the right one shows up to do it.
Let routing decide, or pick your own
The default is smart routing: you write a prompt, Skynet reads it, and chooses the model that fits, balancing quality, speed, and cost. When you’d rather drive, pin a model for the whole conversation, or switch to a different one mid-thread without losing context or history.
Open Chat and just type
Write your prompt without picking a model first. Routing makes the call.
Pin a model when it matters
Doing something where the model choice is the whole point? Open the model picker and pin a specific one for the conversation.
Switch mid-thread to compare
Swap models on your next message. The thread and its context carry over, so you’re comparing answers on the same problem.
What the catalog gives you
- Smart routing: one prompt, the right model, balanced for quality, speed, and cost.
- Pinning and mid-chat switching: override the default without losing context.
- New releases on arrival: frontier models land in your catalog as they ship, no extra subscription.
- Fine-tuning: adapt a model to your data when off-the-shelf isn’t close enough.
- Credit-based pricing: every model has a per-task price, shown as you go.