Stigg Product Updates logo

Product Updates

Back to Homepage Subscribe to Updates

Labels

  • All Posts

Jump to Month

  • October 2026
  • September 2026
  • August 2026
  • July 2026
  • June 2026
  • April 2026
  • March 2026
  • February 2026
  • January 2026
  • December 2025
  • November 2025
  • September 2025
  • August 2025
  • July 2025
  • June 2025
  • April 2025
  • March 2025
  • February 2025
  • January 2025
  • December 2024
  • November 2024
  • October 2024
  • September 2024
  • August 2024
  • July 2024
  • June 2024
  • May 2024
  • April 2024
  • March 2024
  • February 2024
  • January 2024
  • December 2023
  • November 2023
  • September 2023
  • August 2023
  • July 2023
  • June 2023
  • May 2023
  • April 2023
  • March 2023
  • February 2023
  • January 2023
  • December 2022
  • November 2022
  • October 2022
  • August 2022
  • July 2022
  • June 2022
today

Credit Reservation & Settlement

You can now reserve credits before an AI operation starts and settle the actual cost once it completes.

With Reserve & Settle, Stigg secures an estimated credit amount upfront, prevents concurrent requests from reserving the same balance, and automatically releases unused credits. It's designed for AI workloads where the final cost isn't known in advance, such as LLM completions, agent runs, and long-running jobs.

🆕 What's new?

  • Reserve credits upfront - Secure an estimated amount before an operation starts, ensuring those credits are available even when multiple requests run concurrently.
  • Settle the actual cost - Consume the credits used when the operation completes, automatically releasing any unused reserved amount.
  • Automatically release expired reservations - Set an expiration time so abandoned or failed operations don't leave credits locked indefinitely.
  • Safely retry requests - Use reservation IDs to prevent duplicate reservations or settlements.
  • Track reserved balances - See reserved credits separately from consumed credits, with a clear record of reservation and settlement activity.

💡 Why it matters

AI workloads don't always have predictable costs. An LLM response might use fewer tokens than expected, an agent might execute multiple steps, or several requests might compete for the same credit balance.

Reserve & Settle lets you secure credits before work begins and charge for actual consumption afterward - without building custom reservation, refund, or reconciliation logic.

⚒️ Get started

  1. Reserve credits - Call the reservation endpoint through Stigg's REST API or SDK before starting your AI operation.
  2. Execute your operation - Run your LLM request, agent workflow, or background job while the reserved credits remain unavailable to other requests.
  3. Settle the actual usage - Use the reservation ID to settle the final credit amount. Any unused reserved credits are automatically released.

Reservations also support expiration timeouts, ensuring abandoned operations don't leave credits locked indefinitely.

📦 Availability

Reserve & Settle is available through Stigg's REST API and REST SDKs.

REST-based SDKs

  • TypeScript: v0.1.0-beta.62
  • Python: v0.1.0-beta.53
  • Go: v0.1.0-beta.54
  • Java: v0.1.0-beta.54
  • Ruby: v0.1.0-beta.59
  • C#: v0.11.0

🍿 See it in action


Avatar of authorNoa Levi