Complete QA audits — we review your project and send back a detailed report.Request a complete audit ›
Simple pricing

Pay for results, not seats.

Free forever for solo QAs. Scale up only when you ship.

Starter

$0/forever

Limited access to every released GoQA testing workflow.

  • Test case generation: 10 generations a month, up to 200 test cases each
  • Website testing: 5 crawls a month, 5 pages per website each month
  • Scheduled audits (they use the same crawl limits), shared reports and badges
  • JSON, Excel and Gherkin (.feature) export
  • AI Assurance Starter self-serve (limited preview, switched on in stages): API and agent-trace testing within monthly limits
  • Community support

Enterprise

Custom

Everything in the platform, sized and priced around how your team ships.

  • Everything in Starter
  • Up to 10,000 test cases per request
  • Unlimited AI generations
  • Website crawls of up to 50 pages
  • Dedicated solutions engineer
AI Assurance · limited preview

Testing LLM apps and agents

AI Assurance is in limited preview. Starter includes limited self-serve testing of APIs and agent traces, switched on in stages; GoQA enables anything more per workspace when you request access.

AI Assurance availability by plan
PlanAI AssuranceHow to get access
StarterLimited self-serve, switched on in stages: API and agent-trace testing within the Starter limitsOpen AI Assurance from your dashboard once Starter self-serve is on for you. For more, request limited-preview access; for a complete audit, email the team.
EnterpriseStarter self-serve, plus what GoQA enables per workspaceRequest limited-preview access. GoQA enables it per workspace and agrees which channels (API, traces, OpenAI judge) are switched on. URL-only testing is not available yet.

Starter self-serve, switched on in stages: test an OpenAI-compatible API you own and your agent's traces, with 20 runs and 500 traces a month, up to 25 prompts a run, 2 API and 2 trace targets, 2 active ingest keys, evidence kept 30 days and you as the only member. URL-only testing and the OpenAI judge are not included; complete audits are requested by email to team@goqa.ai.

There is no published price for AI Assurance and nothing to buy at checkout. Beyond Starter self-serve, access is by request while it is in limited preview.

What each connection level adds

Each level adds evidence and the workflow stays the same. URL-only testing is not available yet; connect an API or send traces.

  1. Evidence depth 1 of 3

    URL-only (black-box)

    URL-only testing is not available yet. When released, GoQA will interact with your chat page only through the visible interface, within the scope you declare.

    Can show

    • Visible answers to bounded, defensive test prompts
    • Refusal quality and disclosure behavior shown in the UI
    • Visible citations, error states and response timing
  2. Evidence depth 2 of 3

    API-connected

    GoQA calls your OpenAI-compatible chat endpoint directly. Credentials are encrypted and never shown again.

    Can show

    • Exact model responses with token usage, cost and latency
    • Configuration sensitivity (temperature, top_p, max tokens, seed)
    • Structured output and schema checks
  3. Evidence depth 3 of 3

    SDK / trace-connected

    Your server sends run, retrieval, tool, agent-step, latency, token, cost and error events through the GoQA SDK.

    Can show

    • Full agent trajectories: tool selection, arguments, order, approvals and delegation
    • Completion claims checked against recorded tool results
    • Loops, budgets, errors and recovery from reported events

What an assessment involves

  1. Step 1 of 6: Authorize the target

  2. Step 2 of 6: Select an approved plan

  3. Step 3 of 6: Run bounded tests

  4. Step 4 of 6: Review evidence and findings

  5. Step 5 of 6: Remediate and retest

  6. Step 6 of 6: Apply a release gate

In order: authorize the target → select an approved plan → run bounded tests → review evidence and findings → remediate and retest → apply a release gate.

This is a readiness assessment with risk findings and test evidence. It is not a compliance certification and does not guarantee that a system is safe. Policy packs are technical test packs, not legal advice.

Compare features

FeatureStarterEnterprise
Released testing workflowsAll, with the limits belowAll
Test cases per request20010,000
AI generations / month10Unlimited
Website crawls5 / month, 5 pages per website each monthUp to 50 pages each
Complete audit by the GoQA teamBy email requestBy email request
Export formatsJSON, Excel, .featureJSON, Excel, .feature
SupportCommunityDedicated CSM
AI Assurance (limited preview)Starter self-serve within its limits, switched on in stagesStarter self-serve; more enabled per workspace on request
Have questions?

Frequently asked

Need something custom? Request a complete audit or email team@goqa.ai.

All plans billed by 13698491 Canada Inc. Prices in USD.