Skip to content
ProductArena

How Lago’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score46/100

Agent-ready 48.1 × 0.30 = 14.43

API quality 60.6 × 0.20 = 12.12

Openness 57.2 × 0.20 = 11.44

Built-in AI 32.7 × 0.15 = 4.91

Automation 18.0 × 0.15 = 2.70

(14.43 + 12.12 + 11.44 + 4.91 + 2.70) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 45.60 ÷ 1.00 = 45.6

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready48.1/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://getlago.com/llms.txt“PROBE llms.txt: HTTP 200 at https://getlago.com/llms.txt # Lago > Lago is the open-source billing platform for usage-based, subscription-based, and hybrid pricing models. Built”
  • [probe] https://getlago.com/docs/api-reference/intro.md“PROBE docs-md: HTTP 200 at https://getlago.com/docs/api-reference/intro.md > ## Documentation Index > Fetch the complete documentation index at: https://getlago.com/docs/llms.txt > Use this file”
  • [probe] https://getlago.com/openapi.json“PROBE openapi: HTTP 200 at https://getlago.com/openapi.json — contains "openapi" key”
  • [probe] https://getlago.com/docs/guide/ai-agents/mcp-server“official MCP server documented at https://getlago.com/docs/guide/ai-agents/mcp-server”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://getlago.com/docs/guide/lago-self-hosted/docker“Docker is the easiest way to get started with the self-hosted version of Lago.”
  • [claimed-docs] https://getlago.com/docs/api-reference/intro“Every endpoint in this reference has a generated command.”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”
  • [github] https://github.com/getlago/lago“It starts the Lago version that matches this checkout, creates a disposable local organization, and prices three illustrative AI requests.”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/dunning-agent“The Dunning Agent reads the account first: twelve months of invoices and payments, the disputes, the provider status.”
  • [probe] https://getlago.com/docs/guide/ai-agents/mcp-server“official MCP server documented at https://getlago.com/docs/guide/ai-agents/mcp-server”

Connect an agent via an official MCP serverweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”
  • [probe] https://getlago.com/docs/guide/ai-agents/mcp-server“official MCP server documented at https://getlago.com/docs/guide/ai-agents/mcp-server”

Use an official CLIweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://getlago.com/docs/api-reference/intro“Every endpoint in this reference has a generated command.”

Drive the product through a documented public APIweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [claimed-docs] https://getlago.com/docs/api-reference/intro“Every endpoint in this reference has a generated command.”
  • [claimed-docs] https://getlago.com/docs/api-reference/versioning“Clients should tolerate additive changes within v1, including new response fields, enum values, endpoints, optional request fields, and webhook event types.”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”
  • [probe] https://getlago.com/llms.txt“PROBE llms.txt: HTTP 200 at https://getlago.com/llms.txt # Lago > Lago is the open-source billing platform for usage-based, subscription-based, and hybrid pricing models. Built”
  • [probe] https://getlago.com/docs/api-reference/intro.md“PROBE docs-md: HTTP 200 at https://getlago.com/docs/api-reference/intro.md > ## Documentation Index > Fetch the complete documentation index at: https://getlago.com/docs/llms.txt > Use this file”
  • [probe] https://getlago.com/openapi.json“PROBE openapi: HTTP 200 at https://getlago.com/openapi.json — contains "openapi" key”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”
  • [probe] https://getlago.com/docs/guide/ai-agents/mcp-server“official MCP server documented at https://getlago.com/docs/guide/ai-agents/mcp-server”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”
  • [probe] https://getlago.com/docs/guide/ai-agents/mcp-server“official MCP server documented at https://getlago.com/docs/guide/ai-agents/mcp-server”

Build against official SDKsweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”
  • [claimed-docs] https://getlago.com/docs/api-reference/intro“Every endpoint in this reference has a generated command.”
  • [probe] https://getlago.com/openapi.json“PROBE openapi: HTTP 200 at https://getlago.com/openapi.json — contains "openapi" key”
  • [claimed-docs] https://getlago.com/docs/api-reference/versioning“Clients should tolerate additive changes within v1, including new response fields, enum values, endpoints, optional request fields, and webhook event types.”

Subscribe to events via webhooksweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://getlago.com/docs/guide/webhooks“The second is `HMAC`, which features a shorter payload header and no size restrictions.”
  • [claimed-docs] https://getlago.com/docs/api-reference/versioning“Clients should tolerate additive changes within v1, including new response fields, enum values, endpoints, optional request fields, and webhook event types.”

Agent-ready = 101.0 ÷ 210 × 100 = 48.1

API quality60.6/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://getlago.com/docs/api-reference/intro“Every endpoint in this reference has a generated command.”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”
  • [probe] https://getlago.com/openapi.json“PROBE openapi: HTTP 200 at https://getlago.com/openapi.json — contains "openapi" key”
  • [probe] https://getlago.com/docs/api-reference/intro.md“PROBE docs-md: HTTP 200 at https://getlago.com/docs/api-reference/intro.md > ## Documentation Index > Fetch the complete documentation index at: https://getlago.com/docs/llms.txt > Use this file”

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://getlago.com/openapi.json“PROBE openapi: HTTP 200 at https://getlago.com/openapi.json — contains "openapi" key”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 4 (quality) × 0.6 (partial) = 2.4 of 10 max

  • [github] https://github.com/getlago/lago“It starts the Lago version that matches this checkout, creates a disposable local organization, and prices three illustrative AI requests.”
  • [claimed-docs] https://getlago.com/docs/guide/lago-self-hosted/docker“Docker is the easiest way to get started with the self-hosted version of Lago.”

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://getlago.com/docs/api-reference/versioning“Clients should tolerate additive changes within v1, including new response fields, enum values, endpoints, optional request fields, and webhook event types.”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”
  • [probe] https://getlago.com/openapi.json“PROBE openapi: HTTP 200 at https://getlago.com/openapi.json — contains "openapi" key”

API quality = 42.4 ÷ 70 × 100 = 60.6

Openness57.2/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 7 (quality) × 0.6 (partial) = 8.4 of 20 max

  • [claimed-docs] https://getlago.com/docs/api-reference/intro“Every endpoint in this reference has a generated command.”
  • [claimed-docs] https://getlago.com/platform/usage-metering“Both non-engineers and engineers can update usage charges via API or Lago’s no-code UI.”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”
  • [probe] https://getlago.com/openapi.json“PROBE openapi: HTTP 200 at https://getlago.com/openapi.json — contains "openapi" key”

Export all of my data in open formats and leaveweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

  • [claimed-docs] https://getlago.com/docs/guide/lago-self-hosted/docker“Docker is the easiest way to get started with the self-hosted version of Lago.”
  • [claimed-docs] https://getlago.com/docs/guide/invoicing/overview“You can download invoices or use the invoice object to create your own invoice template.”
  • [claimed-docs] https://getlago.com/platform/revenue-analytics“Build custom dashboards per customer, filter any way you want and export to CSV.”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”
  • [probe] https://getlago.com/openapi.json“PROBE openapi: HTTP 200 at https://getlago.com/openapi.json — contains "openapi" key”

Read the product's source under an open licenseweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [probe] https://getlago.com/llms.txt“PROBE llms.txt: HTTP 200 at https://getlago.com/llms.txt # Lago > Lago is the open-source billing platform for usage-based, subscription-based, and hybrid pricing models. Built”
  • [github] https://github.com/getlago/lago“It starts the Lago version that matches this checkout, creates a disposable local organization, and prices three illustrative AI requests.”

Self-host the core productweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://getlago.com/docs/guide/lago-self-hosted/docker“Docker is the easiest way to get started with the self-hosted version of Lago.”
  • [community] https://news.ycombinator.com/item?id=34773442“"This looks great... Stripe is awesome but a self-hosted option fits our culture and philosophy a lot better. Will give it a blast when i get a chance."”
  • [community] https://news.ycombinator.com/item?id=39957607“"Looks very interesting. We are small shop and self-hosting is not an issue. This neatly fits a requirement we've had for quite some time."”

Openness = 57.2 ÷ 100 × 100 = 57.2

Built-in AI32.7/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/dunning-agent“The Dunning Agent reads the account first: twelve months of invoices and payments, the disputes, the provider status.”
  • [probe] https://getlago.com/docs/guide/ai-agents/mcp-server“official MCP server documented at https://getlago.com/docs/guide/ai-agents/mcp-server”

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/dunning-agent“The Dunning Agent reads the account first: twelve months of invoices and payments, the disputes, the provider status.”
  • [probe] https://getlago.com/docs/guide/ai-agents/mcp-server“official MCP server documented at https://getlago.com/docs/guide/ai-agents/mcp-server”

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/dunning-agent“The Dunning Agent reads the account first: twelve months of invoices and payments, the disputes, the provider status.”
  • [probe] https://getlago.com/docs/guide/ai-agents/mcp-server“official MCP server documented at https://getlago.com/docs/guide/ai-agents/mcp-server”

Operate the product with natural-language commandsweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/dunning-agent“The Dunning Agent reads the account first: twelve months of invoices and payments, the disputes, the provider status.”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”
  • [probe] https://getlago.com/docs/guide/ai-agents/mcp-server“official MCP server documented at https://getlago.com/docs/guide/ai-agents/mcp-server”

Built-in AI = 29.4 ÷ 90 × 100 = 32.7

Automation18.0/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://getlago.com/docs/api-reference/intro“Every endpoint in this reference has a generated command.”
  • [claimed-docs] https://getlago.com/developers“Use Lago's OpenAPI 3.1 schema to generate clients, inspect typed operations, or expose billing actions to an AI agent.”

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://getlago.com/docs/guide/webhooks“The second is `HMAC`, which features a shorter payload header and no size restrictions.”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/dunning-agent“The Dunning Agent reads the account first: twelve months of invoices and payments, the disputes, the provider status.”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”

Schedule recurring jobs or workflowsweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [claimed-docs] https://getlago.com/docs/guide/plans/plan-model“Yearly: subscription fees are billed on a yearly basis and charges can be billed monthly or annually.”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/dunning-agent“The Dunning Agent reads the account first: twelve months of invoices and payments, the disputes, the provider status.”
  • [claimed-docs] https://getlago.com/docs/guide/ai-agents/mcp-server“provides AI assistants (like Claude) with direct access to Lago’s billing data.”

Version, review, and roll back my automationsweight 1

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 12.6 ÷ 70 × 100 = 18.0