Make (formerly Integromat)
The friendliest way to put AI agents to work across 3,500+ apps — as long as you watch the credit meter and don't need self-hosting or real evals.
PRICING
| Free | Free | up to 1,000 credits/mo, 2 active scenarios |
| Core | $12/mo | 10,000 credits/mo |
| Pro | $21/mo | 10,000 credits/mo |
| Teams | $38/mo | 10,000 credits/mo |
| Enterprise | Custom | sales-led |
Billing is per credit (one module action = one credit), and every paid price is the entry point of a slider running from 10,000 up to 8M+ credits per month, so the real bill depends on volume. Make advertises "save 15% or more" for annual billing; the page shows a single set of figures and does not publish the second set, so the $12/$21/$38 above are the prices as displayed.
checked 2026-07-25 · vendor pricing page
Element scores
Strengths
The widest no-code tool surface in the category: AI agents that call any of 3,521 app modules plus external MCP tools in one reasoning loop, a mature visual harness (routers, iterators, error handlers, subscenarios), fast frontier-model onboarding, and a native Knowledge RAG store. Make Grid adds fleet-level visibility for teams running dozens of automations, and agents are available on every plan including Free.
Honest dings
Credits burn fast on multi-step and AI-heavy workflows (native AI actions cost multiple credits; Code app is 2 credits/second), audit logs are locked behind Enterprise and log retention is ~30 days below it, there is no evaluation surface for AI outputs at all, no self-hosting, and multi-agent coordination is chaining, not primitives. The August 2025 operations→credits switch left recurring pricing-opacity complaints in reviews.
Sources (12) — every claim traceable
Every audit lists the research it rests on — transparency and traceability are the product. Tools evolve: each audit is a snapshot of its audit date, and re-audits supersede older versions (kept below for reference).
- make.com/en/pricing — Plan tiers, credit allowances, full-text log search Pro+, audit logs Enterprise-only, data-transfer limits (accessed 2026-07-05)
- make.com/en/ai-agents — AI Agents product page: all-plans availability, 3,000+ apps, model lineup, Feb 2026 next-gen launch (accessed 2026-07-05)
- make.com/en/blog/announcing-next-generation-make-ai… — Next-generation Make AI Agents announcement, 11/02/2026 (accessed 2026-07-05)
- community.make.com/t/feature-spotlight-add-mcp-tool… — External MCP servers as agent tools (June 2026); prior MCP Client/Server/Toolboxes timeline (accessed 2026-07-05)
- help.make.com/2026 — 2026 changelog: GPT-5.4 (nano/mini), Claude Opus 4.8, Gemini 3.1 Pro, MCP toolboxes, Make Grid updates, 2FA enforcement (accessed 2026-07-05)
- help.make.com/knowledge — Knowledge feature: managed RAG vector store for AI agents, upload/manage, credit usage (accessed 2026-07-05)
- developers.make.com/api-documentation/api-reference… — AI Agents API (open beta): create/run agents, SSE streaming (accessed 2026-07-05)
- make.com/en/blog/2024-automation-wrap-up — Official user stats: 3.1M users (+68% YoY), 5.6B scenario runs in 2024 (accessed 2026-07-05)
- hackdvisor.com/reviews/make — Independent review: 3,521 apps (June 2026), 400k+ orgs homepage claim, credits switch 27/08/2025, Celonis ownership (accessed 2026-07-05)
- modernoutreach.beehiiv.com/p/make-review — Independent review: AI Agents + Maia launch Oct 2025, Make Grid beta, G2 4.6/Capterra 4.8 ratings (accessed 2026-07-05)
- zapier.com/blog/make-com-pricing — Independent (competitor) breakdown of credit mechanics: per-step billing, Code app 2 credits/sec, AI actions cost more (accessed 2026-07-05)
- community.make.com/t/is-it-possible-to-have-data-hi… — Execution history detail: per-module I/O inspection, JSON export, replay; 30-day retention below Enterprise (accessed 2026-07-05)