BFL auto top-up ($5 threshold) vs Sume dashboard top-ups
BFL can recharge credits automatically below a threshold of at least $5. Sume top-ups are manual dashboard actions, and concurrency is set by plan only.
BFL added auto top-up on August 27, 2026: set a threshold (minimum $5) and a target (at least $10 above it), and your saved card is charged whenever the balance drops below the threshold. Sume has no equivalent in its public API: a top-up is a manual, Stripe-backed action in the dashboard, and the Developer API exposes balance and usage reads only.
BFL details are from its release notes; Sume details from Billing and credits and Generation admission, read 2026-10-01.
How does BFL's auto top-up work?
| Setting | Rule in the release notes |
|---|---|
| When balance falls below | The balance that triggers a recharge, minimum $5 |
| Recharge balance to | The balance after a recharge, at least $10 above the threshold |
| Receipts | Automatic recharges appear in Purchase History with invoices |
What does Sume do about top-ups?
The dashboard can initiate a Stripe-backed manual credit top-up when billing is configured for the workspace. The docs say API clients should treat top-ups as dashboard operations: the public Developer API currently exposes balance and usage reads, not a top-up creation endpoint. So you cannot script a recharge; monitor GET /v1/balance and top up in the dashboard.
Does a top-up raise my concurrency?
No. Generation concurrency is plan-only; prepaid top-ups do not raise the processing concurrency limit. If you run out of balance, a request returns 402 insufficient_credits, and the docs say not to invent prepaid top-ups as the remedy there; upgrade the plan, wait for included Gen$, or submit a cheaper request.
What should I do to avoid running dry?
Poll GET /v1/balance on a schedule, alert on your own threshold, and top up from the dashboard before a batch. A comparable case is covered in Synthesia auto top-up vs Sume top-ups.
Sources
Related posts
More in Pricing
- Cartesia Sonic 3.6 heteronyms: read, bass, live, and Sume pricing
Sonic 3.6 improves English heteronyms like read, bass and live in context. When context is enough, when to use a dictionary id, and Sume's TTS rate.
- Cheapest AI video API model on Sume: 5-second clips ranked
Grok Imagine 1.5 is the cheapest 5-second clip on Sume at 480p, then Gemini Omni Flash at 360p and Wan 3.0. Ten models ranked by reserved amount.
- Managed Agents budget_reached vs Sume generation_spend_cap_usd
A Managed Agents session budget caps spend at list rates and pauses with budget_reached. Sume's generation_spend_cap_usd is a separate required cap.
- Workers AI paid models 20/min, 50 with prepaid vs Sume plans
Cloudflare lifts paid Workers AI models from 20 to 50 requests per minute with prepaid credits. On Sume, top-ups do not raise concurrency; the plan does.
Written by Sume