How the credit wallet works

Your wallet is denominated in real dollars with an always-visible live meter, so you can see what you are spending as you spend it. Each model shows its $/message rate before you send.

Fast vs premium

• Fast models (for example Mistral Small) are the lowest-priced band. Every message is billed at the $/message rate shown on the model — there is no free tier.
• Premium models (for example Claude Sonnet 4.6, GPT-5.5, Gemini 3.5 Flash) cost more — typically 10–25× a budget-band message, and flagship models more still — so they draw from a paced premium budget. Every model's exact per-message price is shown in the picker.

How the premium budget is paced

• A $5.00 premium budget a month, released 25% per week so a busy day can’t consume the whole month at once. How many messages that buys depends on the model you pick — budget-band models cost a fraction of a cent per message, flagships cost more (each model’s per-message price is shown in the picker).
• Each week’s premium allotment expires at the end of that week — it doesn’t roll over, so the best value is using it as it’s released.

When premium runs low

• At 80% of the week's premium, you get an announced warning banner — never a silent change. If you have enabled it, knecty can auto-switch you to a lower-priced model (you can set this default in Settings → Models).
• At $0 premium, knecty offers your cheapest chargeable option and draws on your top-up balance. If neither balance can cover a message, we say so honestly and pause until you top up or your next weekly release — we never serve a message we’d have to silently absorb.

Deep Research and other agentic work are metered in a separate token pool, so they never quietly eat your premium messages.