Skip to content

Coming from Dify?

Dify offers a node canvas, a knowledge layer, an agent mode and apps you publish and self-host. On Whenever you describe the same automation in plain language and AI writes one typed TypeScript module. AI building is free within weekly usage limits; the file is yours. Review summaries and sample results; reading code is optional. Fixed logic is deterministic with the same inputs and dependencies, while changing external data and optional AI can change results and costs.

What you get on Whenever

  • One module, written for you

    Describe the automation in plain language and get one typed TypeScript module, with every step in the same file.

  • Hosted by Whenever

    Whenever runs published workflows for you, with managed credentials for supported connections and stored secrets for other APIs. Dify also offers hosted plans; compare deployment, workflow and model-provider requirements rather than treating self-hosting as compulsory.

  • Runs, and the AI you add

    You are metered when a workflow runs, and a run counts once however many API calls the code makes. AI building is free within weekly usage limits. If you add a model step, it draws on the plan’s separate AI allowance — so there are two numbers, and both are in dollars.

A concrete decision

Illustrative scenarios, not customer results or recorded runs.

  • Greg: no “done” without the invoice receipt

    Illustrative decision, not a recorded customer run: Greg wants each paid order checked against Stripe, then an invoice created, its ID saved, and only then a confirmation sent. He specifies that an invoice failure must stop the confirmation, and an already-handled order must not be charged or invoiced again. He checks the summary, sample records, provider receipts and run history—not source code. Test a missing payment, a failed invoice and a duplicate event before publishing. Whenever fits when those prescribed steps matter more than an agent deciding them again; a fixed workflow elsewhere can fit too. No screenshot here claims these actions were actually delivered.

  • Jaunius: make the edge cases explicit

    Illustrative decision, not a benchmark: Jaunius needs all pages of 5,000 contacts, a saved last-seen ID, updates only for changed records and a clear record of which writes failed. He brings the old workflow and sample inputs, reconnects accounts, and tests pagination, an API failure and a repeated event before switching triggers. Choose a single procedure if it makes this logic easier to maintain; the other tools can also support complex logic. An optional model that classifies a note can vary and adds runtime AI usage. Compare the monthly subscription and actual usage, not the number of steps alone.

A node canvas. A file of TypeScript.

Dify hosted plans list message credits and trigger events, with own-provider keys as an alternative for model usage. Whenever meters workflow runs and runtime AI separately. Compare the configured workload.

Dify

Cloud message credits + trigger events

Message credits and trigger events; own model keys bill through the provider

Hosted plans list message credits and trigger events. Provider keys and self-hosted deployment change which usage bills you pay.

Whenever

See current pricing

10,000 runs per month

Find the right plan for you
Loading price…

Hosted message credits and trigger events count different work. Dify supports its AI credits or your own model-provider keys, with priority and fallback settings. Self-hosting involves infrastructure and provider usage under the Dify licence; read the licence for deployment and branding restrictions rather than assuming unrestricted Apache terms.

A run is one execution of one workflow, start to finish. AI building and editing are free within weekly usage limits; runs are metered separately.

A closer look

What changes when you describe the job in plain language and code runs it: to build, to run, and to keep.

Repeatable execution logic

Dify

A published workflow runs the nodes you arranged, in the order you arranged them; Dify’s own framing is “AI capabilities within a structured, repeatable process”. An LLM or Agent node is model-directed exactly where you place one.

Whenever

AI writes it, then published code runs the same execution logic. With identical inputs and dependencies, non-AI logic is deterministic. Changing API data, time, randomness or an optional model step can change results; this is not an exactly-once delivery guarantee.

Runs per dollar

Dify

Hosted plan quotas distinguish message credits and trigger events. Model-provider key configuration can move model usage to your provider bill; include both platform and provider charges.

Whenever

Pro includes 10,000 runs per month; see the pricing page for current US dollar prices. AI building and editing are free within weekly usage limits. Published runs are metered separately: the meter counts the whole run, not individual steps. External services and optional model calls can have their own charges.

What you can express

Dify

Dify documents a workflow canvas with logic, HTTP requests, Python or JavaScript Code nodes and knowledge retrieval. Automatic triggers apply to Workflow apps; Chatflow and the beta Agent app cover other modes.

Whenever

Describe the job in plain language: match payments to orders, fetch every page of contacts, or alert only on unseen reviews. AI writes the procedure; you supervise its rules and results, and reading code is optional. API access still needs suitable permissions and a service reachable from the hosted runtime.

Export and portability

Dify

Dify exports apps as YAML DSL for import into Dify. The documentation distinguishes app configuration from knowledge content; secret inclusion is configurable. Keep credentials out of shared exports and confirm what the selected export includes.

Whenever

The TypeScript is yours: read it, edit it, export it, take it with you. Moving it to another runtime can require adapting managed connections, triggers and runtime-specific integrations.

Debugging a failed run

Dify

Dify documents run history and tracing, single-node tests, a variable inspector and error-handling paths. The Code node documentation includes automatic retry settings; do not assume identical retry support for every node.

Whenever

Read the procedure and its execution log side by side, then re-test the failing input. External data and any explicit model call still have to be accounted for when reproducing a failure.

Where the AI cost lands

Dify

Dify supports hosted AI credits and your own provider keys, with configurable priority and fallback. Check which provider handles each call and which plan allowance it draws on.

Whenever

AI writes the workflow once, with free building subject to weekly AI usage limits. A published procedure runs its steps without a model choosing them. Any model call you explicitly include still runs and has its own cost.

When to keep Dify

Dify

Keep it when retrieval is the point: knowledge bases, chunking and indexing settings, retrieval testing and the knowledge pipeline are a product here, not an integration you assemble. Keep it when non-engineers need to read and change the automation on the same canvas the engineer built, and when self-hosting the whole stack in your own VPC matters.

Whenever

Consider Whenever when the job is a business procedure you want to supervise through rules and results rather than an AI application. Code remains available for a developer; reading a diff is not required. It does not provide a built-in knowledge base or hosted chat app.

One schedule per workflow

Dify

Dify documents at most one schedule trigger per workflow, alongside webhook and app-event triggers that can run in parallel. Sandbox accounts are capped at two triggers per workflow; Professional and Team allow more.

Whenever

A workflow can be published on a schedule, a webhook or on demand, and a second schedule is a second workflow either way.

Sources and scope

Official sources captured on the date shown below. These describe published features and billing rules, not independent performance tests. Check the linked documentation for current modes, plans and limits. No competitor dollar price is asserted.

Checked

Start with a workflow brief

Pick a starting point, connect your accounts and review what Whenever builds before publishing.

Bring every lead source into one CRM recordCollects new leads from Typeform and a Google Sheets tab and creates or updates a single HubSpot contact with its original source.Build this workflowAnnounce closed-won deals in SlackCelebrates each won deal in Slack with the numbers and a short recap of how it was won.Build this workflowPublish Instagram posts from a calendarPublishes due rows from your Instagram calendar on the cadence you choose and writes each post link back.Build this workflowLog survey responses and alert on low scoresAdds each survey response to Google Sheets within minutes and emails the owner when the score falls below your threshold.Build this workflowTrack keyword rankings in a sheet each weekChecks the search position of every keyword on your list, appends the history to a sheet and reports the moves.Build this workflowRoute large expense claims to a managerLogs every expense submission in a sheet and alerts a manager in Slack when the amount is over the approval limit.Build this workflow
Browse all templates

Start with one Dify workflow.

Bring one workflow and its test inputs. Describe it once, and Whenever writes it as TypeScript you can review and download.

Build free

  1. Export the app and read the DSL

    Use the YAML DSL as a specification of nodes, branches and model settings. Check what the export includes and remove secrets before sharing it; knowledge content requires separate migration planning.

  2. Split retrieval from procedure

    Decide which steps genuinely need the knowledge base and which are API calls and rules. Describe the second half to Whenever, review the TypeScript, and reconnect each service.

  3. Run both against the same inputs

    Compare outputs on representative events, including the empty and malformed cases. Switch the Dify trigger off in the app’s access point before publishing the replacement, so one event does not do the work twice.