# Model Ruler — LLM-inference-ops calculators

> Deterministic cost and capacity calculators for LLM inference operators.
> Open formula. Browser-based calculations. Source-dated rates. No API keys. No provider login. No tracing SDK. No account required. Input payloads are not stored.

## MCP / API Surface

- POST https://modelruler.dev/mcp — JSON-RPC 2.0 (tools/list + tools/call)
- POST https://modelruler.dev/calculate/{tool}/ — REST shorthand
- GET  https://modelruler.dev/openapi-modelruler.json — OpenAPI spec

## Tools (12)

- token-counter: Use when a user asks how many tokens a given text will consume, or needs to estimate prompt size before pricing a workload.
- provider-cost-calculator: Use when a user asks what an LLM workload costs on a specific provider/model, or wants to compare cost across providers.
- self-host-breakeven-calculator: Use when a user is deciding between API usage and self-hosted GPU inference at a given volume.
- context-window-planner: Use when a user needs to know whether a document plus prompt plus output fits within a model's context window, or wants a strategy recommendation (truncate/summarize/rag/chunk).
- quantization-calculator: Use when a user is planning to quantize an LLM to fit on smaller hardware.
- fine-tune-roi-calculator: Use when a user is considering fine-tuning vs prompt engineering.
- eval-cost-calculator: Use when a user needs to budget an LLM evaluation run.
- observability-cost-calculator: Use when a user needs to budget LLM observability tooling.
- rag-pipeline-cost-calculator: Use when a user needs end-to-end RAG cost estimation (embedding + vector store + generation).
- automation-cost-calculator: Use when a user needs to compare workflow automation platform cost across Zapier task billing, Make credit billing, and n8n execution billing for a recurring workflow shape.
- agent-workflow-cost-calculator: Use when a user needs to estimate automation-platform cost for an agent workflow, including app-action fan-out and MCP tool-call accounting, separate from LLM token spend.
- agent-loop-cost-calculator: Use when a user is running multi-step LLM agents and needs cost per successful task.

## Contract
Every tool returns: low_estimate, high_estimate, interpretation, next_step,
next_step_url, why_follow_up, severity (healthy|moderate|significant|major|critical),
related_tools, _chain_meta, computation_basis.