Pricing

Every operation available in the dashboard is also available via REST. Fire comparisons, evaluations, and benchmark runs from any script, pipeline, or CI workflow. Developer keys are available on all plans from your account page.

The MCP server is one way to reach LLM Prover, alongside the dashboard and the REST API. It exposes the tools to any MCP-capable AI agent – Claude Desktop, Cursor, VS Code Copilot, Amazon Q – which discovers them automatically and drives your runs in plain language, with no integration code. MCP is available on Pro and above.

Scoring judges text you already have – a draft, a reply, a clause – against a rubric or your compliance documents, and returns a per-criterion verdict. Paste one piece, or several to rank them against one standard. Scoring is on Pro and above; compliance scoring is on Pro Plus and above.

Agent analysis is how LLM Prover does agent evaluation. It reads the trace of an agent workflow (the step-by-step record of what your agent did), checks every step, and shows where the workflow wasted money, time or effort and which step caused it. It reads Kiro and Claude Code traces. It is on Pro, Pro+ and Enterprise, not on Starter, and it counts toward your plan’s usage.

A preset is a saved run configuration – models, scoring method, rubric, context – that you build once and then invoke by name from the dashboard, the API, or a plain-language ask to your agent. A curated starter preset ships ready to run. Presets are on Pro and above.

Usage is the cost of the model calls LLM Prover makes on your behalf – input and output tokens billed at provider rates. It does not include LLM Prover’s platform fee, which is your monthly subscription. You can see current provider rates on the AI API pricing pages.

Runs stop. You can purchase a top-up from your account page immediately – no downtime, no data loss. Top-ups are consumed as you run and carry over month to month. They are not refundable.

No. Top-ups carry over indefinitely and are consumed as you run. Your monthly included usage resets every billing anniversary. Top-ups do not reset – they accumulate until used.

Yes. Cancel from your account page or billing portal at any time. Stripe will apply a credit to your account for the unused portion of your subscription. You can use that credit against a future charge, or continue using the service until the end of the paid term with no further charges after that.

Pro adds rubric evaluation, daily benchmarks, alert thresholds, RAG stores, and one BYOE endpoint. Pro+ adds compliance rubric scoring, 4x daily benchmark frequency, five RAG stores, five BYOE endpoints, and bulk export.

Features above your new tier are locked immediately. Extra RAG stores and compliance stores created on Pro+ are preserved but paused – you can access them again if you upgrade. The dashboard shows a downgrade preview before you confirm so you know exactly what changes.

Any account can create an org and invite members via email. Each member’s usage draws from their own plan allowance. If you want members to be able to draw from your top-up balance when their allowance runs out, you enable that in the org settings. The org owner sees all member usage in one place. One subscription, one invoice.

No. Prompts and outputs are stored to power your result history and drift analysis. They are not used to train any model.

Enterprise plans are configured to your team size and use case. Get in touch at /contact.