Replit
Desktop app for Mac, Windows and Linux. Agents run on your computer or in the vendor's cloud.
Product websitereplit.com Compare with others Missing or wrong data?
- Desktop app
- Mac, Windows and Linux
- Browser
- Yes
- Phone
- IPhone, Android and phone browser
- Command line
- Not listed
- Agents
- Not listed
- Your subscription
- Not listed
- Agents run
- On your computer and in the vendor's cloud
- Laptop closed
- Keeps going
- Isolation
- Container and VM
- Parallel agents
- Yes
- Scheduled runs
- Yes
- Coordinator agent
- Yes
- Built-in issues
- Yes
- Pull requests
- Yes
- Review screen
- Yes
- Team
- Roles and SSO
- Self-hosting
- No
- Licence
- Proprietary
- Price from
- Free
- How it charges
- Free plan, subscription, usage-based and per machine or compute
- Paid plans from
- $11–20/month
Receipts
- Checked
- · oldest answer 2026-11-08
- Findings
- 42 published · 28 cross-checked by a second agent · read them all
- Sources
- 56 public pages on 3 sites: docs.replit.com, replit.com, cdn.replit.com
- Screenshot
- docs.replit.com, retrieved · first party docs · shows appearance, not capability
- Data
- /products/replit.json · .md
- Method
- Same rules for all 103 researched ADEs. How we check · Report wrong data
What it does
Where you use it
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
Source and scope for Where you use itAgents it runs
The documented development experience runs Replit Agent with selectable modes/models. The checked sources do not establish named third-party coding-harness integrations; building an app that calls a provider or installing arbitrary shell software is separate.
Source and scope for Agents it runsAccounts and subscriptions
Replit plan credits pay for Agent. User API keys power calls made by built apps, while the Agent itself remains Replit-managed rather than using the app API keys. A native external coding-agent subscription login remains unestablished.
Source and scope for Accounts and subscriptionsWhere agents run
Replit provides managed cloud development, and the current desktop page also offers local Agent code/build execution on supported Mac/Windows devices. Full BYOC Agent execution is private preview, while published-app exports do not move development.
Source and scope for Where agents runHow work is kept apart
Replit repository development sandboxes explicitly use microVMs. Its current local desktop offering names Microsoft Execution Containers on supported Mac/Windows devices; background task copies are not established as Git worktrees.
Source and scope for How work is kept apartParallel work
Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.
Source and scope for Parallel workScheduled runs
Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.
Source and scope for Scheduled runsGit and pull requests
The repository contribution workflow creates branches, commits/pushes code and opens draft GitHub PRs or GitLab MRs, then can revise the same request after review.
Source and scope for Git and pull requestsLicence and source
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
Source and scope for Licence and sourcePrice
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
Source and scope for PriceTyped filters
Every value links to its receipt below. Read plan and surface restrictions before using a filter to decide.
| Filter | Value |
|---|---|
| Desktop OS: macOS | Yes |
| Desktop OS: Windows | Yes |
| Desktop OS: Linux | Yes |
| Web client | Yes |
| Phone access: Native iOS | Yes |
| Phone access: Native Android | Yes |
| Phone access: Phone browser | Yes |
| CLI | Unknown |
| Coding agents: Claude Code | Unknown |
| Coding agents: Codex | Unknown |
| Coding agents: Cursor Agent | Unknown |
| Coding agents: Gemini CLI | Unknown |
| Coding agents: OpenCode | Unknown |
| Coding agents: Pi | Unknown |
| Coding agents: Grok | Unknown |
| Coding agents: Aider | Unknown |
| Coding agents: Antigravity | Unknown |
| Use my subscription | Unknown |
| Where agents run: On your computer | Yes |
| Where agents run: On your own server | No |
| Where agents run: In the vendor's cloud | Yes |
| Workspace isolation: Git worktree | Unknown |
| Workspace isolation: Container | Yes |
| Workspace isolation: VM or microVM | Yes |
| Parallel runs | Yes cross-checked |
| Coordinator | Yes cross-checked |
| Native issue tracking | Yes cross-checked |
| Unattended triggers | Yes cross-checked |
| Shared prompting | Unknown |
| Team roles | Yes cross-checked |
| SSO | Yes cross-checked |
| Pull request workflow | Yes |
| Review interface | Yes |
| Product license: Apache-2.0 | No. Proprietary |
| Product license: MIT | No. Proprietary |
| Product license: GPL-3.0 | No. Proprietary |
| Product license: GPL-3.0-or-later | No. Proprietary |
| Product license: AGPL-3.0 | No. Proprietary |
| Product license: AGPL-3.0-or-later | No. Proprietary |
| Product license: Elastic License 2.0 | No. Proprietary |
| Product license: Custom terms | No. Proprietary |
| Product license: Proprietary | Yes. Proprietary |
| Self-hosting | No |
| Telemetry opt-out | Unknown |
| Free access | Yes cross-checked |
| Starting price: Free | Yes. Free cross-checked |
| Starting price: Up to $20/month | No. Free cross-checked |
| Starting price: $21–40/month | No. Free cross-checked |
| Starting price: $41–100/month | No. Free cross-checked |
| Starting price: Over $100/month | No. Free cross-checked |
| Starting price: Contact for pricing | No. Free cross-checked |
| Pricing model: Free, no paid plan | No |
| Pricing model: Free plan | Yes cross-checked |
| Pricing model: Subscription | Yes |
| Pricing model: Per seat | No |
| Pricing model: Usage-based | Yes |
| Pricing model: Per machine or compute | Yes |
| Pricing model: Bring your own key | No |
| Pricing model: One-time purchase | No |
| Paid plans from: No paid plan | No. $11–20/month |
| Paid plans from: $10 or less/month | No. $11–20/month |
| Paid plans from: $11–20/month | Yes. $11–20/month |
| Paid plans from: $21–40/month | No. $11–20/month |
| Paid plans from: $41–100/month | No. $11–20/month |
| Paid plans from: Over $100/month | No. $11–20/month |
| Paid plans from: Contact sales | No. $11–20/month |
| Lifecycle status: Active | Unknown |
| Lifecycle status: Sunsetting | Unknown |
| Keeps going with laptop closed | Yes |
| Open-source license | No. Proprietary |
| Any desktop app | Yes |
| Paid plan up to $20/month | Yes. $11–20/month |
| Paid plan up to $40/month | Yes. $11–20/month |
| Any phone client | Yes |
Filter receipts
Desktop OS: macOS: Yes
Desktop OS: macOS
Typed value: Yes.
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Desktop os: The current native desktop guide explicitly supports Mac, Windows and Debian-based Linux.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Replit: What is the Replit Desktop App; install and sync
Finding: The current first-party desktop guide explicitly offers a native app for Windows, Mac and Debian-based Linux, including Agent, Project Editor and publishing. This establishes desktop clients rather than inferring them from a companion CLI.
Desktop OS: Windows: Yes
Desktop OS: Windows
Typed value: Yes.
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Desktop os: The current native desktop guide explicitly supports Mac, Windows and Debian-based Linux.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Replit: What is the Replit Desktop App; install and sync
Finding: The current first-party desktop guide explicitly offers a native app for Windows, Mac and Debian-based Linux, including Agent, Project Editor and publishing. This establishes desktop clients rather than inferring them from a companion CLI.
Desktop OS: Linux: Yes
Desktop OS: Linux
Typed value: Yes.
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Desktop os: The current native desktop guide explicitly supports Mac, Windows and Debian-based Linux.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Replit: What is the Replit Desktop App; install and sync
Finding: The current first-party desktop guide explicitly offers a native app for Windows, Mac and Debian-based Linux, including Agent, Project Editor and publishing. This establishes desktop clients rather than inferring them from a companion CLI.
Web client: Yes
Web client
Typed value: Yes.
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Mobile apps: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Browser: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
- Task actions: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
- Notifications: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Cross device continuity: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Finding: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
-
Replit: Mobile features; Navigate your project
Finding: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
Phone access: Native iOS: Yes
Phone access: Native iOS
Typed value: Yes.
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Mobile apps: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Browser: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
- Task actions: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
- Notifications: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Cross device continuity: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Finding: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
-
Replit: Mobile features; Navigate your project
Finding: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
Phone access: Native Android: Yes
Phone access: Native Android
Typed value: Yes.
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Mobile apps: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Browser: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
- Task actions: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
- Notifications: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Cross device continuity: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Finding: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
-
Replit: Mobile features; Navigate your project
Finding: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
Phone access: Phone browser: Yes
Phone access: Phone browser
Typed value: Yes.
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Mobile browser: The first-party code editor page explicitly offers the cloud development workspace in a phone browser.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Replit: From your browser or mobile phone
Finding: The first-party AI code editor page explicitly offers the full cloud development workspace from a browser on desktop or mobile devices, alongside the native mobile apps.
Where agents run: On your computer: Yes
Where agents run: On your computer
Typed value: Yes.
Replit provides managed cloud development, and the current desktop page also offers local Agent code/build execution on supported Mac/Windows devices. Full BYOC Agent execution is private preview, while published-app exports do not move development.
- Local: The desktop product page explicitly offers Agent build/run in the selected local environment on supported Mac/Windows devices.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: self_hosted, hybrid, provisioning, payer, resources, region, expiry, other_device_continuation.
-
Replit: Build locally; Isolate builds in local sandboxes
Finding: The current desktop product page explicitly says Agent can build and run apps using the local environment and selected local folders. On supported Windows and macOS devices it names Microsoft Execution Containers for code/build-tool isolation. This does not establish a Linux local-execution sandbox.
Where agents run: On your own server: No
Where agents run: On your own server
Typed value: No.
Replit provides managed cloud development, and the current desktop page also offers local Agent code/build execution on supported Mac/Windows devices. Full BYOC Agent execution is private preview, while published-app exports do not move development.
- Byo remote: The currently described Full BYOC Agent runtime is private preview; published-app BYOC/exports do not provide public Agent execution on an operator server.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: self_hosted, hybrid, provisioning, payer, resources, region, expiry, other_device_continuation.
-
Replit: Compare deployment options; Full BYOC warning and availability
Finding: Full BYOC includes Agent/development execution in a customer tenant but is explicitly private preview, with eligibility/configurations confirmed through Enterprise onboarding. Published-app BYOC and Image Exports are early access and do not move the development/Agent control plane. Even Full BYOC leaves the control plane external and explicitly is not an entirely self-hosted or air-gapped Replit installation.
Where agents run: In the vendor's cloud: Yes
Where agents run: In the vendor's cloud
Typed value: Yes.
Replit provides managed cloud development, and the current desktop page also offers local Agent code/build execution on supported Mac/Windows devices. Full BYOC Agent execution is private preview, while published-app exports do not move development.
- Client disconnect: The cloud Project Editor retains project state and running app when the browser closes; this does not establish unlimited Agent runtime.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: self_hosted, hybrid, provisioning, payer, resources, region, expiry, other_device_continuation.
-
Replit: Frequently asked questions
Finding: The cloud Project Editor saves files, history and the running app when the browser closes. This documents cloud persistence, not an unlimited Agent process lifetime.
Workspace isolation: Container: Yes
Workspace isolation: Container
Typed value: Yes.
Replit repository development sandboxes explicitly use microVMs. Its current local desktop offering names Microsoft Execution Containers on supported Mac/Windows devices; background task copies are not established as Git worktrees.
- Container: The desktop page explicitly names Microsoft Execution Containers for local code/build execution on supported Windows/macOS devices.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: branch, worktree, os_sandbox, filesystem, process, network, secrets, security_boundary.
-
Replit: Build locally; Isolate builds in local sandboxes
Finding: The current desktop product page explicitly says Agent can build and run apps using the local environment and selected local folders. On supported Windows and macOS devices it names Microsoft Execution Containers for code/build-tool isolation. This does not establish a Linux local-execution sandbox.
Workspace isolation: VM or microVM: Yes
Workspace isolation: VM or microVM
Typed value: Yes.
Replit repository development sandboxes explicitly use microVMs. Its current local desktop offering names Microsoft Execution Containers on supported Mac/Windows devices; background task copies are not established as Git worktrees.
- Vm: The repository-development guide explicitly names a microVM boundary.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: branch, worktree, os_sandbox, filesystem, process, network, secrets, security_boundary.
-
Replit: Sandbox architecture; draft PR and review workflow
Finding: The current repository-contribution guide explicitly says the development sandbox runs in a microVM. Replit owns the contribution workflow: it creates a branch, commits/pushes changes, opens a GitHub draft PR or GitLab MR, and updates the request after review.
Parallel runs: Yes cross-checked
Parallel runs
Typed value: Yes.
Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.
- Concurrent sessions: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.
- Concurrent tasks: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.
- Quotas: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.
- Status visibility: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Tasks start running; Availability
Finding: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.
Coordinator: Yes cross-checked
Coordinator
Typed value: Yes.
Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.
- Results return: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.
- Orchestration owner: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.
- Activation: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.
- Live progress: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What is the task system; Review and apply
Finding: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.
Native issue tracking: Yes cross-checked
Native issue tracking
Typed value: Yes.
Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
- Create: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
- Archive: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
- Reopen: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
- Project epic views: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
- Explicit dispatch: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
- Task session separation: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
- Durable states: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What is the task system; Frequently asked questions
Finding: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
Unattended triggers: Yes cross-checked
Unattended triggers
Typed value: Yes.
Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.
- Schedules: Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.
- Recurring tasks: Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.
- Overlaps: Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: How Routines run; Availability and limits
Finding: Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.
Team roles: Yes cross-checked
Team roles
Typed value: Yes.
Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members. SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
- Organization roles: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members.
- Membership: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members.
- Sso: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
- Provisioning: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
- Plan scope: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Personal vs. team workspaces; Managing members
Finding: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members.
-
Replit: Configure single sign-on
Finding: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
SSO: Yes cross-checked
SSO
Typed value: Yes.
Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members. SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
- Organization roles: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members.
- Membership: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members.
- Sso: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
- Provisioning: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
- Plan scope: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Personal vs. team workspaces; Managing members
Finding: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members.
-
Replit: Configure single sign-on
Finding: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
Pull request workflow: Yes
Pull request workflow
Typed value: Yes.
The repository contribution workflow creates branches, commits/pushes code and opens draft GitHub PRs or GitLab MRs, then can revise the same request after review.
- Branches: Replit creates the contribution branch in its owned repository workflow.
- Commits: The workflow commits and pushes the contribution.
- Pull requests: It opens a draft PR/MR and links it in the product Changes/Details interface.
- Comments: Review follow-up can update the same request and reply to review comments.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: worktrees, ci_response, rebase, product_state.
-
Replit: Sandbox architecture; draft PR and review workflow
Finding: The current repository-contribution guide explicitly says the development sandbox runs in a microVM. Replit owns the contribution workflow: it creates a branch, commits/pushes changes, opens a GitHub draft PR or GitLab MR, and updates the request after review.
-
Replit: Changes and pull requests
Finding: The product Changes pane switches between local changes and linked pull requests, shows branch/description details and renders the proposed code diff with added/removed lines. Linked requests also appear in Details and review feedback can be addressed through Agent.
Review interface: Yes
Review interface
Typed value: Yes.
Replit displays code diffs in its Changes pane, alongside local changes or linked PRs, in addition to task logs, tests and previews for review decisions.
- Change understanding: Changes displays proposed-code additions/deletions and linked PR metadata; local and PR diffs are product-rendered.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: evidence_navigation, comments, request_changes, effort, missed_evidence, keyboard, narrow_screen, context_switching, roles, retained_context.
-
Replit: Changes and pull requests
Finding: The product Changes pane switches between local changes and linked pull requests, shows branch/description details and renders the proposed code diff with added/removed lines. Linked requests also appear in Details and review feedback can be addressed through Agent.
Product license: Apache-2.0: No. Proprietary
Product license: Apache-2.0
Typed value: No. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Product license: MIT: No. Proprietary
Product license: MIT
Typed value: No. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Product license: GPL-3.0: No. Proprietary
Product license: GPL-3.0
Typed value: No. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Product license: GPL-3.0-or-later: No. Proprietary
Product license: GPL-3.0-or-later
Typed value: No. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Product license: AGPL-3.0: No. Proprietary
Product license: AGPL-3.0
Typed value: No. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Product license: AGPL-3.0-or-later: No. Proprietary
Product license: AGPL-3.0-or-later
Typed value: No. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Product license: Elastic License 2.0: No. Proprietary
Product license: Elastic License 2.0
Typed value: No. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Product license: Custom terms: No. Proprietary
Product license: Custom terms
Typed value: No. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Product license: Proprietary: Yes. Proprietary
Product license: Proprietary
Typed value: Yes. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Self-hosting: No
Self-hosting
Typed value: No.
Replit imports/exports project artifacts and offers Enterprise deployment options, but even Full BYOC explicitly leaves the control plane external and does not provide an entirely self-hosted Replit installation.
- Self hosting: The BYOC guide explicitly says Full BYOC is not an entirely self-hosted or air-gapped Replit installation.
- Vendor dependencies: Full BYOC keeps an external Replit control plane and managed model inference; published-app export is a separate artifact deployment.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: export, formats, cancellation, account_independence, history_portability.
-
Replit: Compare deployment options; Full BYOC warning and availability
Finding: Full BYOC includes Agent/development execution in a customer tenant but is explicitly private preview, with eligibility/configurations confirmed through Enterprise onboarding. Published-app BYOC and Image Exports are early access and do not move the development/Agent control plane. Even Full BYOC leaves the control plane external and explicitly is not an entirely self-hosted or air-gapped Replit installation.
Free access: Yes cross-checked
Free access
Typed value: Yes.
Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Ongoing free: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Free scenarios: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Usage caps: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What you get; Limitations
Finding: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
Starting price: Free: Yes. Free cross-checked
Starting price: Free
Typed value: Yes. Free.
Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Ongoing free: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Free scenarios: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Usage caps: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What you get; Limitations
Finding: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
Starting price: Up to $20/month: No. Free cross-checked
Starting price: Up to $20/month
Typed value: No. Free.
Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Ongoing free: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Free scenarios: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Usage caps: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What you get; Limitations
Finding: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
Starting price: $21–40/month: No. Free cross-checked
Starting price: $21–40/month
Typed value: No. Free.
Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Ongoing free: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Free scenarios: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Usage caps: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What you get; Limitations
Finding: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
Starting price: $41–100/month: No. Free cross-checked
Starting price: $41–100/month
Typed value: No. Free.
Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Ongoing free: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Free scenarios: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Usage caps: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What you get; Limitations
Finding: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
Starting price: Over $100/month: No. Free cross-checked
Starting price: Over $100/month
Typed value: No. Free.
Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Ongoing free: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Free scenarios: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Usage caps: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What you get; Limitations
Finding: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
Starting price: Contact for pricing: No. Free cross-checked
Starting price: Contact for pricing
Typed value: No. Free.
Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Ongoing free: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Free scenarios: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Usage caps: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What you get; Limitations
Finding: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
Pricing model: Free, no paid plan: No
Pricing model: Free, no paid plan
Typed value: No.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Seats: Pro includes up to 15 builders with no per-user fees.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Tiered monthly credits; up to 15 builders; no per-user fees
Finding: The current Pro documentation explicitly supplies a flat recurring team plan with tiered monthly credits and up to 15 builders, with no per-user fees. Core/Pro subscriptions and usage credits are documented; one-off credit-pack top-ups are prepaid consumption rather than a one-time software license.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
Pricing model: Free plan: Yes cross-checked
Pricing model: Free plan
Typed value: Yes.
Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Ongoing free: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Free scenarios: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Usage caps: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What you get; Limitations
Finding: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
Pricing model: Subscription: Yes
Pricing model: Subscription
Typed value: Yes.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Seats: Pro includes up to 15 builders with no per-user fees.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Tiered monthly credits; up to 15 builders; no per-user fees
Finding: The current Pro documentation explicitly supplies a flat recurring team plan with tiered monthly credits and up to 15 builders, with no per-user fees. Core/Pro subscriptions and usage credits are documented; one-off credit-pack top-ups are prepaid consumption rather than a one-time software license.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
Pricing model: Per seat: No
Pricing model: Per seat
Typed value: No.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Seats: Pro includes up to 15 builders with no per-user fees.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Tiered monthly credits; up to 15 builders; no per-user fees
Finding: The current Pro documentation explicitly supplies a flat recurring team plan with tiered monthly credits and up to 15 builders, with no per-user fees. Core/Pro subscriptions and usage credits are documented; one-off credit-pack top-ups are prepaid consumption rather than a one-time software license.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
Pricing model: Usage-based: Yes
Pricing model: Usage-based
Typed value: Yes.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Credits: Monthly plan credits cover Agent and other cloud services such as published apps, storage and databases.
- Overages: Core monthly credits also let users pay as they go, and credit packs can be bought; the cited pages state no overage rate.
- Compute cost: Cloud services such as published apps, storage and databases draw on the same plan credits as Agent under usage-based billing.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Finding: Monthly plan credits cover Agent and other cloud services such as published apps, storage and databases under usage-based billing, with alerts, budget limits and purchasable credit packs. The page does not list network transfer or state an overage rate.
Pricing model: Per machine or compute: Yes
Pricing model: Per machine or compute
Typed value: Yes.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Credits: Monthly plan credits cover Agent and other cloud services such as published apps, storage and databases.
- Overages: Core monthly credits also let users pay as they go, and credit packs can be bought; the cited pages state no overage rate.
- Compute cost: Cloud services such as published apps, storage and databases draw on the same plan credits as Agent under usage-based billing.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Finding: Monthly plan credits cover Agent and other cloud services such as published apps, storage and databases under usage-based billing, with alerts, budget limits and purchasable credit packs. The page does not list network transfer or state an overage rate.
Pricing model: Bring your own key: No
Pricing model: Bring your own key
Typed value: No.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Model cost: The Replit Agent itself is billed through Replit credits; app provider-key charges are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Can I use my own API keys with Agent?
Finding: The first-party FAQ separates app API credentials from the Agent itself: user provider keys in Secrets power calls made by the built app, while the Agent experience uses Replit-managed model infrastructure rather than the user-key route. Curated in-product model selection is separate from replacing that infrastructure with an independently keyed endpoint. Replit AI billing charges its own plan credits. This is not evidence of a third-party coding harness or a native subscription-login path.
Pricing model: One-time purchase: No
Pricing model: One-time purchase
Typed value: No.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Seats: Pro includes up to 15 builders with no per-user fees.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Tiered monthly credits; up to 15 builders; no per-user fees
Finding: The current Pro documentation explicitly supplies a flat recurring team plan with tiered monthly credits and up to 15 builders, with no per-user fees. Core/Pro subscriptions and usage credits are documented; one-off credit-pack top-ups are prepaid consumption rather than a one-time software license.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
Paid plans from: No paid plan: No. $11–20/month
Paid plans from: No paid plan
Typed value: No. $11–20/month.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Currency: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
Paid plans from: $10 or less/month: No. $11–20/month
Paid plans from: $10 or less/month
Typed value: No. $11–20/month.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Currency: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
Paid plans from: $11–20/month: Yes. $11–20/month
Paid plans from: $11–20/month
Typed value: Yes. $11–20/month.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Currency: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
Paid plans from: $21–40/month: No. $11–20/month
Paid plans from: $21–40/month
Typed value: No. $11–20/month.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Currency: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
Paid plans from: $41–100/month: No. $11–20/month
Paid plans from: $41–100/month
Typed value: No. $11–20/month.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Currency: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
Paid plans from: Over $100/month: No. $11–20/month
Paid plans from: Over $100/month
Typed value: No. $11–20/month.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Currency: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
Paid plans from: Contact sales: No. $11–20/month
Paid plans from: Contact sales
Typed value: No. $11–20/month.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Currency: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
Keeps going with laptop closed: Yes
Keeps going with laptop closed
Typed value: Yes.
Replit provides managed cloud development, and the current desktop page also offers local Agent code/build execution on supported Mac/Windows devices. Full BYOC Agent execution is private preview, while published-app exports do not move development.
- Managed cloud: Repository development runs in Replit cloud sandboxes.
- Client disconnect: The cloud Project Editor retains project state and running app when the browser closes; this does not establish unlimited Agent runtime.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: self_hosted, hybrid, provisioning, payer, resources, region, expiry, other_device_continuation.
-
Replit: Frequently asked questions
Finding: The cloud Project Editor saves files, history and the running app when the browser closes. This documents cloud persistence, not an unlimited Agent process lifetime.
-
Replit: Sandbox architecture; draft PR and review workflow
Finding: The current repository-contribution guide explicitly says the development sandbox runs in a microVM. Replit owns the contribution workflow: it creates a branch, commits/pushes changes, opens a GitHub draft PR or GitLab MR, and updates the request after review.
Open-source license: No. Proprietary
Open-source license
Typed value: No. Proprietary.
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Server license: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement.
- Source visibility: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
Any desktop app: Yes
Any desktop app
Typed value: Yes.
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Desktop os: The current native desktop guide explicitly supports Mac, Windows and Debian-based Linux.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Replit: What is the Replit Desktop App; install and sync
Finding: The current first-party desktop guide explicitly offers a native app for Windows, Mac and Debian-based Linux, including Agent, Project Editor and publishing. This establishes desktop clients rather than inferring them from a companion CLI.
Paid plan up to $20/month: Yes. $11–20/month
Paid plan up to $20/month
Typed value: Yes. $11–20/month.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Currency: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
Paid plan up to $40/month: Yes. $11–20/month
Paid plan up to $40/month
Typed value: Yes. $11–20/month.
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Currency: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation.
- Interval: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
Any phone client: Yes
Any phone client
Typed value: Yes.
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Mobile apps: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Browser: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
- Task actions: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
- Notifications: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Cross device continuity: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Finding: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
-
Replit: Mobile features; Navigate your project
Finding: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
All public findings
Findings may summarize a source. They are not presented as verbatim statements.
replit:ACC-01: Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
replit:ACC-01
Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.
-
Finding: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.
-
Replit: Mobile features; Navigate your project
Finding: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.
-
Replit: What is the Replit Desktop App; install and sync
Finding: The current first-party desktop guide explicitly offers a native app for Windows, Mac and Debian-based Linux, including Agent, Project Editor and publishing. This establishes desktop clients rather than inferring them from a companion CLI.
-
Replit: From your browser or mobile phone
Finding: The first-party AI code editor page explicitly offers the full cloud development workspace from a browser on desktop or mobile devices, alongside the native mobile apps.
replit:ACC-02: The documented development experience runs Replit Agent with selectable modes/models. The checked sources do not establish named third-party coding-harness integrations; building an app that calls a provider or installing arbitrary shell software is separate.
replit:ACC-02
The documented development experience runs Replit Agent with selectable modes/models. The checked sources do not establish named third-party coding-harness integrations; building an app that calls a provider or installing arbitrary shell software is separate.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: custom_adapters, session_integration, mixed_harness_operation.
-
Finding: Replit Agent has Free, Power and Max modes; Auto routes paid work to models. Model routing does not establish support for a third-party coding harness.
-
Replit: Can I use my own API keys with Agent?
Finding: The first-party FAQ separates app API credentials from the Agent itself: user provider keys in Secrets power calls made by the built app, while the Agent experience uses Replit-managed model infrastructure rather than the user-key route. Curated in-product model selection is separate from replacing that infrastructure with an independently keyed endpoint. Replit AI billing charges its own plan credits. This is not evidence of a third-party coding harness or a native subscription-login path.
replit:ACC-03: Replit plan credits pay for Agent. User API keys power calls made by built apps, while the Agent itself remains Replit-managed rather than using the app API keys. A native external coding-agent subscription login remains unestablished.
replit:ACC-03
Replit plan credits pay for Agent. User API keys power calls made by built apps, while the Agent itself remains Replit-managed rather than using the app API keys. A native external coding-agent subscription login remains unestablished.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: local_models, account_switching, vendor_account_requirement, provider_restrictions.
-
Finding: Replit plan credits pay for Agent and other cloud services; paid actions use effort-based pricing after confirmation.
-
Replit: Can I use my own API keys with Agent?
Finding: The first-party FAQ separates app API credentials from the Agent itself: user provider keys in Secrets power calls made by the built app, while the Agent experience uses Replit-managed model infrastructure rather than the user-key route. Curated in-product model selection is separate from replacing that infrastructure with an independently keyed endpoint. Replit AI billing charges its own plan credits. This is not evidence of a third-party coding harness or a native subscription-login path.
replit:ACC-04: Start a project by describing an idea in plain language, or bring it in from GitHub, Figma or uploaded files, in the cloud Project Editor.
replit:ACC-04
Start a project by describing an idea in plain language, or bring it in from GitHub, Figma or uploaded files, in the cloud Project Editor.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Getting started; Import code and design
Finding: Start a project by describing an idea in plain language, or bring it in from GitHub, Figma or uploaded files, in the cloud Project Editor. The page names no templates and does not itself state that no local environment is needed.
replit:PLAN-01: A main-thread prompt can create titled tasks with descriptions and plans, or users can start a planning thread. cross-checked
replit:PLAN-01
A main-thread prompt can create titled tasks with descriptions and plans, or users can start a planning thread.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: How background tasks work
Finding: A main-thread prompt can create titled tasks with descriptions and plans, or users can start a planning thread.
replit:PLAN-02: Agent proposes detailed plans and definitions of done; users inspect View plan, accept tasks or request a revised plan before execution. cross-checked
replit:PLAN-02
Agent proposes detailed plans and definitions of done; users inspect View plan, accept tasks or request a revised plan before execution.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Plan your tasks; Review and accept
Finding: Agent proposes detailed plans and definitions of done; users inspect View plan, accept tasks or request a revised plan before execution.
replit:PLAN-03: Agent identifies prerequisite tasks and queues dependent work until the prerequisite is applied. The board shows the blocker. cross-checked
replit:PLAN-03
Agent identifies prerequisite tasks and queues dependent work until the prerequisite is applied. The board shows the blocker.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Create and approve remaining tasks; Let Agent schedule the work
Finding: Agent identifies prerequisite tasks and queues dependent work until the prerequisite is applied. The board shows the blocker.
replit:PLAN-04: Each background task inherits the project context and receives its own Agent and project copy. cross-checked
replit:PLAN-04
Each background task inherits the project context and receives its own Agent and project copy.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Your app is safe while tasks run
Finding: Each background task inherits the project context and receives its own Agent and project copy.
replit:PLAN-05: Projects can begin from GitHub, Figma or uploaded files; this establishes input channels, not verified architecture comprehension. cross-checked
replit:PLAN-05
Projects can begin from GitHub, Figma or uploaded files; this establishes input channels, not verified architecture comprehension.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Import code and design
Finding: Projects can begin from GitHub, Figma or uploaded files; this establishes input channels, not verified architecture comprehension.
replit:PLAN-06: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it. cross-checked
replit:PLAN-06
Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What is the task system; Frequently asked questions
Finding: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.
replit:PLAN-07: Agent can split a request into tasks and put them on the human-visible task board. cross-checked
replit:PLAN-07
Agent can split a request into tasks and put them on the human-visible task board.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What is the task system
Finding: Agent can split a request into tasks and put them on the human-visible task board.
replit:COORD-01: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue. cross-checked
replit:COORD-01
Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Tasks start running; Availability
Finding: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.
replit:COORD-02: Agent schedules independent tasks when capacity exists and holds dependent tasks until prerequisites are applied. cross-checked
replit:COORD-02
Agent schedules independent tasks when capacity exists and holds dependent tasks until prerequisites are applied.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Let Agent schedule the work
Finding: Agent schedules independent tasks when capacity exists and holds dependent tasks until prerequisites are applied.
replit:COORD-03: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow. cross-checked
replit:COORD-03
Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What is the task system; Review and apply
Finding: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.
replit:COORD-04: Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing. cross-checked
replit:COORD-04
Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: How Routines run; Availability and limits
Finding: Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.
replit:COORD-05: Cancel stops building and discards its work. The main thread and each task thread permit follow-up direction. cross-checked
replit:COORD-05
Cancel stops building and discards its work. The main thread and each task thread permit follow-up direction.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Frequently asked questions
Finding: Cancel stops building and discards its work. The main thread and each task thread permit follow-up direction.
replit:COORD-06: A project board displays Drafts, Active, Ready and Done tasks alongside task conversations. Fleet-scale navigation has not been tested. cross-checked
replit:COORD-06
A project board displays Drafts, Active, Ready and Done tasks alongside task conversations. Fleet-scale navigation has not been tested.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: A project board displays Drafts, Active, Ready and Done tasks alongside task conversations. Fleet-scale navigation has not been tested.
replit:COORD-07: Users start with ordinary chat, refine plans and let Agent create task lists before approving work. cross-checked
replit:COORD-07
Users start with ordinary chat, refine plans and let Agent create task lists before approving work.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Plan mode; What you can build
Finding: Users start with ordinary chat, refine plans and let Agent create task lists before approving work.
replit:RUN-01: Replit provides managed cloud development, and the current desktop page also offers local Agent code/build execution on supported Mac/Windows devices. Full BYOC Agent execution is private preview, while published-app exports do not move development.
replit:RUN-01
Replit provides managed cloud development, and the current desktop page also offers local Agent code/build execution on supported Mac/Windows devices. Full BYOC Agent execution is private preview, while published-app exports do not move development.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: self_hosted, hybrid, provisioning, payer, resources, region, expiry, other_device_continuation.
-
Replit: Frequently asked questions
Finding: The cloud Project Editor saves files, history and the running app when the browser closes. This documents cloud persistence, not an unlimited Agent process lifetime.
-
Replit: Build locally; Isolate builds in local sandboxes
Finding: The current desktop product page explicitly says Agent can build and run apps using the local environment and selected local folders. On supported Windows and macOS devices it names Microsoft Execution Containers for code/build-tool isolation. This does not establish a Linux local-execution sandbox.
-
Replit: Compare deployment options; Full BYOC warning and availability
Finding: Full BYOC includes Agent/development execution in a customer tenant but is explicitly private preview, with eligibility/configurations confirmed through Enterprise onboarding. Published-app BYOC and Image Exports are early access and do not move the development/Agent control plane. Even Full BYOC leaves the control plane external and explicitly is not an entirely self-hosted or air-gapped Replit installation.
-
Replit: Sandbox architecture; draft PR and review workflow
Finding: The current repository-contribution guide explicitly says the development sandbox runs in a microVM. Replit owns the contribution workflow: it creates a branch, commits/pushes changes, opens a GitHub draft PR or GitLab MR, and updates the request after review.
replit:RUN-02: Replit repository development sandboxes explicitly use microVMs. Its current local desktop offering names Microsoft Execution Containers on supported Mac/Windows devices; background task copies are not established as Git worktrees.
replit:RUN-02
Replit repository development sandboxes explicitly use microVMs. Its current local desktop offering names Microsoft Execution Containers on supported Mac/Windows devices; background task copies are not established as Git worktrees.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: branch, worktree, os_sandbox, filesystem, process, network, secrets, security_boundary.
-
Finding: Background tasks run in isolated project copies and do not change the main version until applied. The docs do not name these copies as containers, VMs or worktrees.
-
Replit: Build locally; Isolate builds in local sandboxes
Finding: The current desktop product page explicitly says Agent can build and run apps using the local environment and selected local folders. On supported Windows and macOS devices it names Microsoft Execution Containers for code/build-tool isolation. This does not establish a Linux local-execution sandbox.
-
Replit: Sandbox architecture; draft PR and review workflow
Finding: The current repository-contribution guide explicitly says the development sandbox runs in a microVM. Replit owns the contribution workflow: it creates a branch, commits/pushes changes, opens a GitHub draft PR or GitLab MR, and updates the request after review.
replit:RUN-03: Files, history and running app are preserved in the cloud for a later visit. No worker-crash recovery test was performed. cross-checked
replit:RUN-03
Files, history and running app are preserved in the cloud for a later visit. No worker-crash recovery test was performed.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What happens when I close my browser?
Finding: Files, history and running app are preserved in the cloud for a later visit. No worker-crash recovery test was performed.
replit:RUN-04: Agent sets up the project and infrastructure. Specific dependency-cache, port-collision and clean-remote-host behavior remains untested. cross-checked
replit:RUN-04
Agent sets up the project and infrastructure. Specific dependency-cache, port-collision and clean-remote-host behavior remains untested.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: Agent sets up the project and infrastructure. Specific dependency-cache, port-collision and clean-remote-host behavior remains untested.
replit:RUN-05: Core and Pro Routines have per-run budgets checked after each step; an in-progress step can complete beyond the budget. Enterprise lacks the per-run budget. cross-checked
replit:RUN-05
Core and Pro Routines have per-run budgets checked after each step; an in-progress step can complete beyond the budget. Enterprise lacks the per-run budget.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: Core and Pro Routines have per-run budgets checked after each step; an in-progress step can complete beyond the budget. Enterprise lacks the per-run budget.
replit:RUN-06: Finished tasks expose a work log, test results and preview; active threads and board cards show task status. cross-checked
replit:RUN-06
Finished tasks expose a work log, test results and preview; active threads and board cards show task status.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: Finished tasks expose a work log, test results and preview; active threads and board cards show task status.
replit:RUN-07: Agent billing is effort-based and uses plan credits shared with cloud services. A controlled reconciliation against provider billing was not performed. cross-checked
replit:RUN-07
Agent billing is effort-based and uses plan credits shared with cloud services. A controlled reconciliation against provider billing was not performed.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: Agent billing is effort-based and uses plan credits shared with cloud services. A controlled reconciliation against provider billing was not performed.
replit:RUN-08: Plan-based task limits cause additional background tasks to queue until slots are available. This is not evidence of per-host CPU or RAM scheduling. cross-checked
replit:RUN-08
Plan-based task limits cause additional background tasks to queue until slots are available. This is not evidence of per-host CPU or RAM scheduling.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: Plan-based task limits cause additional background tasks to queue until slots are available. This is not evidence of per-host CPU or RAM scheduling.
replit:TEAM-01: Invited teammates work on one project through separate Agent threads and shared task boards. Multiple humans steering the same active Agent conversation or work item remains unestablished.
replit:TEAM-01
Invited teammates work on one project through separate Agent threads and shared task boards. Multiple humans steering the same active Agent conversation or work item remains unestablished.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: discussion, comments, presence, ordering, conflicts, attribution, owner_online.
-
Replit: Personal vs. team workspaces
Finding: Team workspaces share projects with members; Core includes five collaboration seats and Pro fifteen. Simultaneous co-prompt ordering is not established by this source.
-
Replit: Build with teammates; independent threads and shared board
Finding: Distinct invited teammates can start their own Agent threads and tasks in the same project, share the board, view history and review/apply ready work. The guide emphasizes separate threads; it does not establish multiple humans sending instructions into the same active Agent conversation/work item.
replit:TEAM-02: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members. SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership. cross-checked
replit:TEAM-02
Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members. SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Personal vs. team workspaces; Managing members
Finding: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members.
-
Replit: Configure single sign-on
Finding: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.
replit:TEAM-03: Humans approve plans before background execution and apply or dismiss finished changes before they affect the main version. cross-checked
replit:TEAM-03
Humans approve plans before background execution and apply or dismiss finished changes before they affect the main version.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Review and accept; Review and apply
Finding: Humans approve plans before background execution and apply or dismiss finished changes before they affect the main version.
replit:TEAM-05: Replit displays code diffs in its Changes pane, alongside local changes or linked PRs, in addition to task logs, tests and previews for review decisions.
replit:TEAM-05
Replit displays code diffs in its Changes pane, alongside local changes or linked PRs, in addition to task logs, tests and previews for review decisions.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: evidence_navigation, comments, request_changes, effort, missed_evidence, keyboard, narrow_screen, context_switching, roles, retained_context.
-
Finding: Ready tasks expose a work log, test results and live preview with Apply or Dismiss decisions. Review effort and missed evidence were not measured.
-
Replit: Changes and pull requests
Finding: The product Changes pane switches between local changes and linked pull requests, shows branch/description details and renders the proposed code diff with added/removed lines. Linked requests also appear in Details and review feedback can be addressed through Agent.
replit:SHIP-01: Task review retains a work log, test results and a live preview in the task flow. A cross-task artifact gallery was not established. cross-checked
replit:SHIP-01
Task review retains a work log, test results and a live preview in the task flow. A cross-task artifact gallery was not established.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: Task review retains a work log, test results and a live preview in the task flow. A cross-task artifact gallery was not established.
replit:SHIP-02: With App Testing enabled, Agent periodically tests apps it builds in an actual browser and fixes issues it finds. It is available for Full Stack JavaScript and Streamlit Python web apps. Documentation is not proof of mandatory independent review or an enforced passing test gate.
replit:SHIP-02
With App Testing enabled, Agent periodically tests apps it builds in an actual browser and fixes issues it finds. It is available for Full Stack JavaScript and Streamlit Python web apps. Documentation is not proof of mandatory independent review or an enforced passing test gate.
- App Testing covers Full Stack JavaScript and Streamlit Python web apps only, and Agent decides when to test rather than testing after every message.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: With App Testing enabled, Agent periodically tests apps it builds in an actual browser and fixes issues it finds; it is available for Full Stack JavaScript and Streamlit Python web apps. Documentation is not proof of mandatory independent review or an enforced passing test gate.
replit:SHIP-03: The repository contribution workflow creates branches, commits/pushes code and opens draft GitHub PRs or GitLab MRs, then can revise the same request after review.
replit:SHIP-03
The repository contribution workflow creates branches, commits/pushes code and opens draft GitHub PRs or GitLab MRs, then can revise the same request after review.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: worktrees, ci_response, rebase, product_state.
-
Finding: Applying tasks invokes AI-assisted conflict resolution. The source does not establish a GitHub PR workflow.
-
Replit: Sandbox architecture; draft PR and review workflow
Finding: The current repository-contribution guide explicitly says the development sandbox runs in a microVM. Replit owns the contribution workflow: it creates a branch, commits/pushes changes, opens a GitHub draft PR or GitLab MR, and updates the request after review.
-
Replit: Changes and pull requests
Finding: The product Changes pane switches between local changes and linked pull requests, shows branch/description details and renders the proposed code diff with added/removed lines. Linked requests also appear in Details and review feedback can be addressed through Agent.
replit:SHIP-04: Users publish to a live URL from the Project Editor. Production authorization and revision binding were not tested. cross-checked
replit:SHIP-04
Users publish to a live URL from the Project Editor. Production authorization and revision binding were not tested.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: How do I publish my app?
Finding: Users publish to a live URL from the Project Editor. Production authorization and revision binding were not tested.
replit:SHIP-05: Agent creates checkpoints that users can roll back to when a change is wrong. cross-checked
replit:SHIP-05
Agent creates checkpoints that users can roll back to when a change is wrong.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What happens if Agent makes a mistake?
Finding: Agent creates checkpoints that users can roll back to when a change is wrong.
replit:OWN-01: The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
replit:OWN-01
The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.
-
Replit: Replit Ownership; limited access rights
Finding: The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.
replit:OWN-02: Replit imports/exports project artifacts and offers Enterprise deployment options, but even Full BYOC explicitly leaves the control plane external and does not provide an entirely self-hosted Replit installation.
replit:OWN-02
Replit imports/exports project artifacts and offers Enterprise deployment options, but even Full BYOC explicitly leaves the control plane external and does not provide an entirely self-hosted Replit installation.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: export, formats, cancellation, account_independence, history_portability.
-
Replit: Import code and design
Finding: Users can import GitHub projects and uploaded files. Exported task history and complete self-hosting are not established.
-
Replit: Compare deployment options; Full BYOC warning and availability
Finding: Full BYOC includes Agent/development execution in a customer tenant but is explicitly private preview, with eligibility/configurations confirmed through Enterprise onboarding. Published-app BYOC and Image Exports are early access and do not move the development/Agent control plane. Even Full BYOC leaves the control plane external and explicitly is not an entirely self-hosted or air-gapped Replit installation.
replit:OWN-03: Pro users can opt out of Model Improvement in Personalization settings, and Replit states it does not train on Enterprise customer content. No such control is named for Starter or Core. This is distinct from telemetry opt-out.
replit:OWN-03
Pro users can opt out of Model Improvement in Personalization settings, and Replit states it does not train on Enterprise customer content. No such control is named for Starter or Core. This is distinct from telemetry opt-out.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: Pro users can opt out of Model Improvement in Personalization settings; Replit states it does not use Enterprise customer content to train models. The page names no such control for Starter or Core.
replit:OWN-04: Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
replit:OWN-04
Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.
-
Finding: Monthly plan credits cover Agent and other cloud services such as published apps, storage and databases under usage-based billing, with alerts, budget limits and purchasable credit packs. The page does not list network transfer or state an overage rate.
-
Finding: Upgrading to Core gives more storage and monthly credits that also let users pay as they go.
-
Replit: Can I use my own API keys with Agent?
Finding: The first-party FAQ separates app API credentials from the Agent itself: user provider keys in Secrets power calls made by the built app, while the Agent experience uses Replit-managed model infrastructure rather than the user-key route. Curated in-product model selection is separate from replacing that infrastructure with an independently keyed endpoint. Replit AI billing charges its own plan credits. This is not evidence of a third-party coding harness or a native subscription-login path.
-
Replit: Tiered monthly credits; up to 15 builders; no per-user fees
Finding: The current Pro documentation explicitly supplies a flat recurring team plan with tiered monthly credits and up to 15 builders, with no per-user fees. Core/Pro subscriptions and usage credits are documented; one-off credit-pack top-ups are prepaid consumption rather than a one-time software license.
-
Replit: Monthly/Yearly Core, Pro and Enterprise plan offering
Finding: The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.
-
Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
Finding: The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.
replit:OWN-06: The November 6 changelog documents Agent-assisted support investigation and Pro ticket submission. This is shipped release activity, not a shutdown notice. cross-checked
replit:OWN-06
The November 6 changelog documents Agent-assisted support investigation and Pro ticket submission. This is shipped release activity, not a shutdown notice.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: Get support directly from Agent
Finding: The November 6 changelog documents Agent-assisted support investigation and Pro ticket submission. This is shipped release activity, not a shutdown notice.
replit:OWN-08: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core. cross-checked
replit:OWN-08
Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Replit: What you get; Limitations
Finding: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.
replit:OWN-09: Agent uses effort-based paid pricing with plan credits; actual charges depend on request complexity and cloud services. A fixed average task price is not documented. cross-checked
replit:OWN-09
Agent uses effort-based paid pricing with plan credits; actual charges depend on request complexity and cloud services. A fixed average task price is not documented.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
-
Finding: Agent uses effort-based paid pricing with plan credits; actual charges depend on request complexity and cloud services. A fixed average task price is not documented.