Skip to main content
Changelog

What's new in ModelSpend.

Product updates, new features, API improvements, and what's shipping next.

June 2026 Beta wave 2

Developer docs, status monitoring, and dashboard improvements

Added
  • Public developer docsdocs.modelspend.best is live with quickstart, API reference, routing concepts, policies, audit logs, error handling, security guide, examples, and SDK overview.
  • Status monitoring pagestatus.modelspend.best provides a public uptime history and incident feed for the proxy, dashboard, and API. Updated at 30‑second intervals.
  • Contextual help popovers — Every dashboard page now has an inline ? help popover explaining the current view, how data is calculated, and what to do next. Available in the top-right of every page header.
  • Provider health tabs — The dashboard status page shows per-provider latency and health with expandable provider tabs. The "View Status Page" link opens the public status site.
  • API key expiry display — The API key table now shows the expiry date for keys configured with a time-limited lifespan. Keys with no expiry show "No expiry".
  • Provider model bulk controls — The Provider Registry now supports model search/filter, select-all-visible, enabled/disabled counts, and bulk enable/disable actions for tenant-owned provider model lists.
Changed
  • Admin tenant selector enforces data scoping — Selecting a tenant in the admin panel now scopes all dashboard data — spend charts, usage tables, routing logs — to that tenant. Previously only the selector UI changed.
  • Dashboard navigation and shell polish — Improved header layout, cleaner page transitions, and consistent status indicator positioning across all viewport sizes.
  • Marketing site improvements — Updated homepage with social proof indicators, benchmark positioning, and an improved ROI calculator layout. Passed a full responsive and accessibility audit at desktop, tablet, and mobile breakpoints.
May 2025 Founding beta

Founding Beta launch

Added
  • OpenAI-compatible proxy — Route AI requests to any supported provider using the same request shape as the OpenAI API. Change one base URL and API key; keep the rest of your code unchanged.
  • Real-time spend dashboard — Visualise token usage, estimated cost, provider breakdown, and 90-day usage history as requests flow through the proxy.
  • Approval workflows — Require team approval for requests that exceed configurable spend thresholds before they are routed to a provider.
  • Model routing rules — Define cost tiers and routing policies to direct requests to the right model based on task type and budget constraints.
  • 90-day usage history and forecast — Spend history with rolling forecast visible from the dashboard overview.

More updates ship regularly during the beta. Join to get early access to every new feature.

Join founding beta

Control AI spend
before it controls you.

Make AI usage measurable before launch. Setup takes 4 minutes. No infrastructure changes.

Route your first call Calculate your savings
Founding Beta: Limited Access
Help shape the future of AI spend control.
ends 29 August 2026
Spots are limited.
Secure your early access.
Request Access