AI spend controls
See the cost before you send.
Pre-send estimates, per-run budgets, per-key caps: transparent, usage-based pricing.
1
Know before you run
Pre-send estimates price the message, and delegated runs carry budget caps: a run stops at its cap.
More about Multi-Model Chat2
Cap every key
API keys carry their own spend caps by day, month, or lifetime, so a leaky script can't drain the balance.
More about AI Gateway3
See where money goes
Every run shows its cost and route; scheduled jobs run under the same caps while you sleep.
More about AutomationsBuilt from these features
AI Gateway
OpenAI-, Anthropic-, and OpenRouter-compatible endpoints with routing you control.
Multi-Model Chat
GPT, Claude, Gemini, Grok, Llama: pick mid-conversation, cheapest-first.
Automations
Delegated runs with schedules, bounded execution, and full progress traces.
Agents
Skills, scoped permissions, persistent memory: any model you pick.