Trying a template or building a new workflow in n8n can suddenly land you on a provider signup page. Before you learn what an unfamiliar node adds, you create an account, add a payment method, generate an API key, and configure credentials. When time is short or you are just exploring, that pause blocks promising ideas before a first run. Now, on self-service n8n Cloud plans, Gateway credits remove that stop and keep you on the canvas.
What are Gateway credits and why do they remove friction?
Gateway credits let you run supported AI nodes in n8n Cloud without signups or keys. Select them instead of your own provider credentials, and usage draws from a shared prepaid balance in n8n. You start working immediately, without creating another account or managing another API key. If you prefer later, bring your own key exactly as before.
We also made the cost side “boring” in a good way. The aim is to follow each provider’s published list price where available and publish all rates on one public page. Your balance shows in real currency, and the Cloud Admin Panel reveals usage by workflow and by service. It is the shortest path from idea to a tool that delivers value today.
For teams, this often means fewer vendor accounts, invoices, and expense reports. One shared balance simplifies life when team policies allow it. Wouldn’t you rather focus on automation than on dashboard management?
There is also less setup with n8n Assistant. You can move from a natural-language prompt to a working workflow, and Gateway credits apply automatically for supported services without existing credentials. Convenient, right?
What gets shared with providers when using Gateway credits?
The selected provider receives only the content of your request, such as a prompt or document. Your identity and n8n account details are not shared. This applies to supported models and tools used via Gateway credits.
This approach lets you test models and services without creating a separate account for each one. You send a task, get a result, and keep sensitive account information within your n8n environment. Want tighter control later? Switch to your own key at any time.
Planning a quick experiment or a team demo? Gateway credits reduce prep steps. You get to a run faster without exposing unnecessary data. Ready to see where this works today?
Where can you use Gateway credits today?
Six model providers and five tool services are available today. You can reach recognized providers like Anthropic, Google Gemini, and OpenAI, or try open models you might have missed. This is only the start, and the list will keep growing.
Among model providers, Alibaba Cloud (Qwen Cloud Node) is available. It helps build coding agents for complex enterprise, research, and long-horizon tasks with the world’s largest open-source model family. There is also Kimi.ai, which takes on long-horizon coding and research tasks, staying on track across many steps with thinking and instant modes.
Another option is MiniMax. Use M3 for coding and agentic work across a 1M-token context, or H3 for omni-modal video generation. Want to test different approaches for one workflow step? You no longer need separate accounts.
Tool services expand your options as well. Brave Search grounds AI apps in real-time results from its own 40-billion-page index — no Google scraping, no upstream dependencies, structural ZDR, and simple, affordable pricing. Browserbase gives your workflows browser agents that navigate, click, type, and extract structured data from the web.
Firecrawl turns websites into LLM-ready data by scraping dynamic pages, parsing media, and crawling entire sites. LlamaParse is agentic OCR that converts complex enterprise documents into structured context at the Pareto frontier of cost and accuracy. PDF.co generates, converts, and extracts PDFs in a single node: HTML to PDF, PDF to structured data, merge, split, and fill.
These eleven providers and services are where we’re starting, not where we’re stopping. Expect the list to keep growing.
How this works in practice: a competitive intelligence workflow
Take a familiar example: a weekly competitive update. Start on the canvas directly or describe the workflow to n8n Assistant in natural language. If you name a supported service and have no credential, the Assistant applies Gateway credits automatically.
Begin with Brave Search. It finds recent product announcements, news coverage, and other changes across the live web. Results come from Brave’s independent index, so the workflow gets current sources to pass into research and analysis. Helpful to ground every report in fresh signals, right?
Next are details that sit behind interactive pricing pages or changelogs that reveal content only after loading or clicks. Browserbase opens those pages in a managed cloud browser, navigates, clicks, types, and extracts required data. A complex, time-consuming task becomes a quick node addition.
Then come documents: product briefs, analyst reports, and PDFs surfaced by search. Basic extractors can flatten careful tables into something unrecognizable, leaving the model with guesswork. LlamaParse combines layout-aware computer vision, OCR, and vision-language models to parse complex documents into structured content that preserves tables, headings, and layouts.
The final step is any supported model. It brings findings together, compares them with last week’s report, highlights changes, and drafts the update. Add your unique parameters, and you have comprehensive intelligence from expert providers without leaving the n8n editor or creating a new account. Need other options? Firecrawl builds knowledge bases, and PDF.co assembles or converts documents in one node.
How do you manage costs, and what comes next?
Gateway credits draw from one balance shared across your n8n instance. That gives you one number to watch and one place to top up. From the Cloud Admin Panel, you can track usage by service and workflow, add funds, or set up automatic top-ups. Instance owners can turn Gateway credits on or off for everyone from Workspace settings.
More choice, less account sprawl. You and your team choose the model or tool that best fits each step, instead of defaulting to what already has credentials. You can see how a new service affects a workflow before committing to another provider account. That’s freedom to test without complicating accounting.
Gateway credits are available on n8n Cloud Starter and Pro today. We also want to bring the same experience to self-hosted instances over time, though that requires additional infrastructure and is not part of this release. Eligible new Cloud accounts, including trials, start with a small balance of Gateway credits. Existing paying Starter and Pro customers received a one-time allowance during the rollout.
Spend it on something you have wanted to try. Put a frontier model from OpenAI, Anthropic, or Google Gemini to work on a new idea. Curious about open models? See what Kimi.ai, Alibaba Cloud, or MiniMax can do in a workflow you already run. Want better web access for an agent? Try Brave Search, Firecrawl, or Browserbase. If documents are the bottleneck, try LlamaParse or PDF.co. Whatever you choose, Gateway credits make it easier to start without leaving the canvas.
Based on the original source.
