AI usage metering & entitlements
Meter tokens/tools/API calls and enforce entitlements for usage-based agent SaaS billing.
At a glance — Oct 2026
Updated 2026-10-27 · forward this page: /jtbds/usage-metering#briefScores as of 2026-09-14 (43 days old; Depot marks scores stale after 30 days). The pick is still Depot's current editorial pick; it has not been re-reviewed since. Prices below carry their own dates.
- Depot Pick
- OpenMeter (Kong Konnect Metering) · 7.93/10 for this job (curated estimate, high confidence)
capability for AI token meters + entitlements. OpenMeter/Kong for API-shaped products; Orb for pricing science; Lago for OSS.
- Runner-up
- Lago · 8.30/10
Scores higher than the pick on: Capability fit, Price / performance, Privacy / data retention, Lock-in risk (higher = worse).
- When not to use the pick
- Simple subscription + basic meters — Stripe Billing; OSS self-host billing — Lago; heavy pricing experimentation/backtests — Orb.
- Lock-in / migration
- Runner-up Lago has lower stored lock-in risk (3 vs 5.5, 0–10, higher = more lock-in).
- Sourced price (no comparable unit)
Pick: no sourced price in this job's unit (no_sourced_price).
No cheapest SKU (no_comparable_unit_for_job). No price was invented.
- Free option
- No free resource lists this job. A cheap paid SKU is not a free option.
- Failure modes to watch
- Confirmation skip: Gate those tool names on an approval id recorded before the call. A missing approval is a failure even if the downstream tool returns success.
- Runaway spend: Set a budget and a tool-call cap per task. Alert when spend jumps. Stop the run at the cap instead of summarizing a partial trace as success.
Cite: Agent Provider Depot, Depot Pick for usage-metering: openmeter, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=usage-metering
OpenMeter (Kong Konnect Metering)
capability for AI token meters + entitlements. OpenMeter/Kong for API-shaped products; Orb for pricing science; Lago for OSS.
Pricing (directional): As of 2026-09-14: OpenMeter Cloud repositioned as Kong Konnect Metering & Billing — real-time AI/API usage meters, entitlements, rate cards, invoicing. Strong fit for token metering via Kong plugin (meter_ai_token_usage). Pricing via Kong/K…
Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.
Best when your agent product is an API gateway problem (entitlements + token meters). Orb for pricing science; Lago for OSS; Stripe for simple SaaS.
Quote for AI usage metering & entitlements
Depot Pick stays OpenMeter (Kong Konnect Metering). Prices below are sourced SKU rows only (as of 2026-10-27). Input and output are not blended. GET /api/quote?jtbd=usage-metering
Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Sourced price unavailable for the Depot Pick. No row in the pricing index.
8 of 8 candidates have no sourced price row. 8 are excluded from the Matching price comparison (none). no comparable sourced unit for this job; chat input $/1M and other units were not borrowed
Runners-up
Lago
Depot OSS pick for AI usage metering when you refuse to marry Stripe's meter model. Still collect cash with…
Orb
Pick Orb when pricing complexity is the product (credits, tiers, simulations). Stripe meters first; Lago if…
Stripe
Non-negotiable for most commercial agent products. Use Billing meters for token pass-through pricing.
Metronome
Strong usage-billing peer when Orb is too sales-opaque and you need SQL metrics + commits. OpenMeter/Kong for…
Autumn
Best DX when you already run Stripe and need synchronous feature gates for AI usage. Metronome/Orb for…
Amberflo
Metering peer when you care about per-customer AI margin, not just invoices. Vantage/CloudZero for cloud…
Polar
Depot pick for ai-merchant-of-record. Prefer Stripe when you already have tax/ops staff; OpenMeter/Kong when…
When NOT to use the top pick
Simple subscription + basic meters — Stripe Billing; OSS self-host billing — Lago; heavy pricing experimentation/backtests — Orb.
Full ranking (score table)
Ranked with this JTBD's weights. Scores are curated estimates unless marked otherwise. Agents: prefer /api/decide then this table for tie-breaks.
| # | Provider | Overall | Fit | $/perf | Latency | DX | As of |
|---|---|---|---|---|---|---|---|
| 1 | Stripe | 8.8 | 9.6 | 7.8 | 9.4 | 9.6 | 2026-09-14 |
| 2 | Lago | 8.3 | 8.6 | 8.8 | 8.0 | 8.0 | 2026-09-14 |
| 3 | Polar | 8.1 | 8.4 | 8.2 | 8.0 | 9.0 | 2026-09-14 |
| 4 | Orb | 8.0 | 9.2 | 6.5 | 9.0 | 8.2 | 2026-09-14 |
| 5 | Metronome | 8.0 | 9.0 | 7.0 | 8.6 | 8.4 | 2026-09-14 |
| 6 | Autumn | 8.0 | 8.0 | 8.8 | 7.8 | 9.2 | 2026-09-14 |
| 7 | OpenMeter (Kong Konnect Metering)Depot Pick | 7.9 | 8.4 | 7.8 | 8.4 | 8.2 | 2026-09-14 |
| 8 | Amberflo | 7.4 | 7.8 | 7.2 | 7.6 | 7.8 | 2026-09-14 |
Score methodology for this job
capability for AI token meters + entitlements. OpenMeter/Kong for API-shaped products; Orb for pricing science; Lago for OSS.
capabilityFit: 25%pricePerformance: 18%latencyReliability: 15%developerDx: 15%privacyPosture: 10%lockInRisk: 7%maturity: 10%