Blink
Also known as: Blink, Blink AI, Blink.new, Blink Claw, Blink AI Gateway, Blink Inc.
AI app builder that turns a prompt into a full stack web or native mobile app with a database, sign in, payments and hosting, plus Blink Claw, always on agents that run on their own cloud machines and work in Slack, Telegram and Discord.
Blink turns a plain English description into a working app. The agent writes a React and TypeScript web app on Vite, or a React Native app with Expo for iOS and Android, and wires in a Turso database, built in sign in, file storage, a Hono backend and Stripe payments. Each finished task updates a private preview and saves a version, and the live app changes only when someone publishes. Blink is backed by Y Combinator and reports more than a million builders and three million apps.
Three other surfaces sit around the builder. Blink Claw is managed hosting for OpenClaw agents, each on its own private machine with a browser, code execution, 1 GB of memory and a secrets vault, working on schedules and in Slack, Telegram and Discord, with 13 ready made agents to start from. A remote MCP server with 37 tools lets Claude, Claude Code or ChatGPT create projects, run builds and publish. Blink Cloud offers the same backend, database, sign in and hosting to developers building with other AI coding tools.
Pricing runs on credits. The free plan gives 5 credits a day up to 30 a month with hosting on a Blink subdomain. Billed annually, Starter costs $13 a month, Pro $25 and Max $100, against $25, $50 and $200 billed monthly, and Business starts at $20 a month billed annually ($40 monthly) for a shared team pool. Production hosting starts at 50 credits a month for up to 10,000 visits, each Claw agent draws its own credits from about $45 a month, and App Store and Google Play publishing comes with Max. Blink is pursuing SOC 2 and has not completed it.
It fits founders, small teams and agencies who want a hosted full stack or mobile app from a description, with agents that keep working after launch. It fits less well where a security review needs a completed SOC 2 report, a choice of data region or single sign on for the team's own logins.
Vendor details
Canonical URL
https://blink.new
Category
Coding agent
Subcategory
AI full stack app builder (vibe coding)
Funding status
Independent, early stage. Blink Inc. is backed by Y Combinator and reports more than a million builders and three million apps built as of August 2026. Funding amounts are undisclosed.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Blink lists 63 connectors across email and newsletters, calendars and meetings, team chat, docs and files, CRM and sales, projects and tasks, design and code, ads and forms, social media, analytics, payments and shops, support and hiring, and AI and the web. A workspace admin connects each tool once, most with a single sign in, and each project picks which accounts it uses. The build agent writes the code that calls them, and calls run through Blink so no token sits in the app. Generated apps also come with a Turso database, Blink Auth, Google Cloud Storage, a Hono backend, Stripe payments and the Blink AI Gateway, and Claw agents reach Notion, Google Drive, HubSpot and Slack.
In practice
You have a SaaS idea but cannot build the backend. You describe it to Blink in plain English, and it ships a working app with a database, sign in, payments and hosting, not a frontend mockup.
You need an internal tool by the end of the week. Blink builds the app, you refine it in chat while the private preview updates, and you publish it to a live address with SSL and a custom domain when it is ready.
You want a phone app as well as a web app. Blink builds it in React Native with Expo, you test it on your own phone through Expo Go, and on Max it builds, signs and sends the iOS version to TestFlight and produces the Android package.
Your inbox and follow ups need handling while you build. You start Maya from Blink Claw, connect Gmail and Slack, and the agent triages mail and drafts replies on its own machine around the clock.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
10.0 / 14 capabilities · 71%
| Integrations & Tool Calling | Full |
|---|---|
|
Every app Blink generates comes wired to a Turso database, Blink Auth sign in, file storage and a live web address with SSL. Beyond that core, 63 connectors across email, calendars, team chat, CRM, projects, payments, analytics and social media are connected once by a workspace admin, most with a single sign in, and each project then picks which accounts it may use. When a builder describes an app, the agent checks which connectors are live and writes the code that reads and sends data through them, and every call is routed through Blink's connector service so no token sits in the app's code. A few tools, among them Meta Ads, ElevenLabs, Perplexity and Firecrawl, take a pasted key instead. Claw agents reach Notion, Google Drive, HubSpot and Slack and send email, and outside assistants can list, authorize and disconnect connectors through Blink's MCP server. Sourceblink.new/integrationsread 2026-10-09 |
|
| Workflow Orchestration | Partial |
|
The build agent runs one multi step loop per request. It plans the change, writes the frontend and backend, sets up the database and sign in, lints and builds the app, and saves a version when the task is done. An outside assistant can start the same loop through the blink_build_prompt tool, follow it with status and wait calls, and answer the agent when it stops on a question, since a new prompt is refused until that question is answered or the build is stopped. Claw agents each run alone on their own machine and can be paused, resized or deleted without touching the others, so several can work in parallel, though they do not hand work to one another or share a plan. Sourceblink.new/docs/cloud/tools/claude-connectorread 2026-10-09 |
|
| Knowledge Grounding & RAG | Partial |
|
Each build works from the project itself: its source tree, database schema, backend functions and saved versions. Blink's MCP server exposes the same material to outside assistants for reading, including file contents, the schema and a diff between any two versions, while secret files such as .env are never returned. Claw agents draw on the workspaces they are connected to, such as Notion and Google Drive. The Knowledge Base in Blink's docs is a retrieval feature for the apps Blink builds, so the build agent keeps no searchable index of a company's wider documents. Sourceblink.new/docs/cloud/tools/claude-connectorread 2026-10-09 |
|
| Human Oversight & Guardrails | Partial |
|
Plan mode lets a builder think a change through with the agent, which only analyzes and replies and does not run tools, write files or deploy, and moving from Plan to Agent asks for confirmation before implementation starts. Agent mode then makes the changes. Production stays apart from the work: each finished task updates a private preview and saves a version, the live app changes only when someone clicks Publish, and any earlier version can be restored and republished. Outside assistants change code only through a full Blink agent turn, since the MCP server has no file write tool, and a viewer's connection is read only. Claw agents act on their own, with the secrets vault setting what each one can reach. Sourceblink.new/docs/reference/modesread 2026-10-09 |
|
| Security, Identity & Governance | Partial |
|
SOC 2 is in progress and not yet complete. The DPA sets out TLS 1.2 or higher with HSTS in transit and AES 256 or equivalent encryption at rest, and, for the company's own production systems, role based access, single sign on, mandatory multi factor authentication, central application and access logs and audit logging on privileged operations, with breach notice within 72 hours. Inside a project, one Owner controls visibility, Admins and deletion, Admins edit with the AI, invite people and publish, and Users can only view. Both roles can be invited on every plan, Free included, with no cap on numbers, and Business adds access levels set per project. None of the plans lists single sign on for logging in to Blink. Sourceblink.new/dparead 2026-10-09 |
|
| Observability & Auditability | Partial |
|
Every finished task saves a version with a screenshot, a generated description of the change, a timestamp and, for projects connected to GitHub, a commit SHA, so a builder can see what the agent changed and when a problem first appeared, then restore a working state. Outside assistants can read the version list, the source tree and a diff between versions over MCP. For apps with a Blink Backend, the Backend tab shows every request live with its route, status code, response time and any error, and function logs can be pulled over MCP. Whether the build agent's individual tool calls are kept as a trace, or a workspace keeps an audit log of agent activity, is unclear. Sourceblink.new/docs/launch/publishread 2026-10-09 |
|
| Memory & State Persistence | Partial |
|
Claw agents keep 1 GB of storage and memory that survives restarts, so preferences, goals and context carry from one conversation to the next, and pausing an agent stops its machine while keeping its data. How that memory is stored, reviewed or cleared is unclear. In the app builder, continuity comes from the project rather than from the agent: every finished task saves a version with a screenshot and a generated description, and the agent rereads the project's code and schema on each request instead of carrying memory of its own across projects. Sourceblink.new/clawread 2026-10-09 |
|
| Deployment & Data Residency | Partial |
|
Core platform data, app databases on Turso, sign in and the build sandboxes sit in the United States on a hosted service. API servers run in the US, the Netherlands and Singapore with requests handled by the nearest one, and Claw agent machines run on Fly.io in US cities, Amsterdam, Frankfurt or London, with each agent's data stored where it runs. Customers do not pick a region. The way off the platform is the code: web apps are standard React and TypeScript on Vite and mobile apps are React Native with Expo, a code download costs 5 credits on Starter and Pro and nothing on Max, and projects sync both ways with GitHub, with the agent's own Git operations coming on Pro, so the code can be taken elsewhere. Sourceblink.new/dparead 2026-10-09 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Blink Claw lists 13 ready made agents, each with its own role, instructions and recommended model, that a customer deploys as they are. For apps, step by step tutorials walk through building a CRM, an analytics dashboard, a project manager, an online store, a course platform and several AI tools, and any public project can be remixed as a starting point. Sourceblink.new/agentsread 2026-10-25 |
|
| Triggers & Channel Coverage | Full |
|
Blink Claw agents run around the clock on a private cloud machine and act on their own schedule, with examples such as a 6:45 AM summary, a 3am inbox check and a Friday report, and on events, such as a follow up sent within ten minutes of a signup. They take messages from Slack, Telegram and Discord, with WhatsApp also listed in the automation docs, can be chatted with inside Blink, and message the user first when something needs attention. How a schedule is set up is unclear. The app builder itself starts work when someone sends a prompt, in the Blink workspace or from Claude, Claude Code or ChatGPT over MCP. Sourceblink.new/clawread 2026-10-09 |
|
| Model Flexibility & Routing | Full |
|
Auto, the recommended setting, routes simple interface changes to fast models, complex features to advanced ones, debugging to reasoning models and design work to models that read images. A builder can switch Auto off and pick the build agent's model directly from Google (Gemini 3 Pro and Flash), OpenAI (GPT-5.2 and GPT-5.1), Anthropic (Claude Opus, Sonnet and Haiku 4.5), xAI (Grok Code Fast) and Z.ai (GLM 4.6), with advanced models included from the Pro plan and costing more credits per request. Claw agents choose separately from 12 models, Claude Sonnet 4.6 by default, and can switch at any time. The AI Gateway's models serve the apps Blink builds rather than the builder. Sourceblink.new/docs/reference/modelsread 2026-10-09 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
A remote MCP server at blink.new/mcp, signed in with OAuth and bound to one workspace, carries scopes for reading the workspace and projects, writing projects and running builds. Its 37 tools cover projects, the database, backend logs, builds, source and versions, publishing, and skills and connectors, so an assistant can start a build, answer the agent's questions, roll back to an earlier version and publish, and setup is laid out for Claude, Claude Code and ChatGPT. Billing, workspace deletion and ownership transfer stay out of reach, and adding secrets or switching models has to happen in the browser. Separately, the AI Gateway API, reached with workspace API keys, gives code chat completions, media generation, web search and file upload. Sourceblink.new/docs/cloud/tools/claude-connectorread 2026-10-09 |
|
| Testing, Debugging & Optimization | Partial |
|
Each finished task runs a lint check and a build before the preview updates and a version is saved, and preview errors are surfaced to the agent and, over MCP, to outside assistants. When something breaks, the agent investigates in chat before changing code, and an earlier version can be restored. In mobile apps, features such as the camera, health data, push notifications and haptics only behave correctly on real hardware, so Blink points builders to testing on a phone through Expo Go. Whether the agent writes and runs its own tests for the app is unclear. Sourceblink.new/docs/launch/publishread 2026-10-09 |
|
| Browser & Computer Use | Full |
|
Since a June 2026 release, Blink's agent clicks through links, dismisses overlays, types into search boxes and moves through multi step forms on live websites to capture real pages. Claw agents come with a web browser beside Python, Node.js and bash for jobs such as prospect research and inbox work. Sourceblink.new/docs/changelogread 2026-10-25 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Version 0.10.0 of Blink CLI adds two commands, blink security table and blink security rls, so a coding agent or developer can set per table read and write rules (owner, public or deny) and scope tables to their row owner from the terminal. Security writes are now path scoped PATCH calls that change only the named module or table, and the CLI refuses to open the ai, agent, rag, queue, sandbox or data modules to signed out callers; the project owner must approve that in the Blink app.
Bears on: Security / enterprise
View sourcePricing
Free plan. Starter from $25 per month, or $13 billed annually.
Credit based. Each plan carries monthly plan credits plus daily refresh credits, spent on AI requests and on production hosting traffic. Business shares one credit pool across unlimited members.
Included quota
Free carries 5 daily credits capped at 30 a month. Starter carries 100 plan credits a month plus daily refresh credits, Pro 200 plan credits, and Max 800 or more with rollover. Business starts from 100 credits in a shared pool. Every plan includes a database, authentication and a live web address, with unlimited team members.
What is public
Plan prices are listed for Free, Starter at $25 a month ($13 billed annually), Pro at $50 ($25), Max from $200 ($100) and Business from $40 ($20), with annual billing at half price. Top up packs run from 100 credits for $40 to 3,750 credits for $1,000 and never expire, and Claw machine tiers cost about $45, $90 and $180 a month. What a single request costs in credits varies with its size and the model behind it.
Billing mechanics
Credits are spent per AI request by complexity and model tier, and on production hosting by traffic. Daily refresh credits reset nightly Pacific time, plan credits carry over only on Max, and Business pools credits across the team.
Cost watchouts
Credits are spent by the size of each request and by model tier, with advanced models such as GPT-5.2 and Claude Opus costing more per request than fast ones, so cost depends on which model the builder runs. Free stops at 30 credits a month. Production hosting is a monthly charge in credits by traffic tier, 50 credits for up to 10,000 visits, 120 for 50,000 and 240 for 200,000. Each Claw agent draws its own monthly credits by machine size, from 180 credits (about $45) to 720 (about $180), with its model use taken from the same balance. Fees are not refunded.
Variable cost rationale
Blink meters credits. Each AI request draws credits by its complexity and model tier, with advanced models costing more than fast ones, and production hosting draws a monthly tier of 50, 120 or 240 credits by traffic. Heavy iteration and growing traffic spend the allowance faster and push an app up a tier. The plan's allowance is the limit. Free stops at 30 credits a month, paid plans add daily refresh credits, and Business pools credits across the team. Unused plan credits carry over only on Max, so on other plans an unused allowance is lost each month.
Additional watchouts
Heavy iteration and advanced models spend credits faster, and hosting draws on the same balance as traffic grows. Below Max, code downloads and custom domains cost 5 credits each, and App Store and Google Play publishing needs Max.
Overage / add-ons
Credits are spent per AI request by complexity and model tier, and on hosting by traffic tier, from 50 credits a month for up to 10,000 visits. Unused plan credits carry over only on Max, so heavier use means a higher tier.
Sales call required
No, self serve available
Free / trial
Free plan with 5 credits a day up to 30 a month, a database, sign in and hosting on a Blink subdomain, no card required
Lowest paid plan
Starter at $25 per month, or $13 per month billed annually.
Commercial notes
The free tier is enough to evaluate Blink and launch on a Blink subdomain.
Key ambiguities
A request has no fixed credit price, so total spend depends on how much building a project needs and which models it uses. The pricing page also gives Max both 800 to 20,000 and 800 to 50,000 monthly credits, and its FAQ ties rollover to Business tiers of 800 credits and up while the plan table gives rollover to Max.
Cancellation / refund
Cancel at any time and keep access until the end of the paid period. Subscription fees are not refunded.
Support SLA / resale
Community support on Free and Starter, priority support on Pro, premium support on Max and VIP support on Business. Blink has no reseller or white label program.
Missing data
The credit cost of an individual request is not published.
Related vendors
- Cognition — Maker of Devin, an autonomous AI software engineer
- 10Web — Agentic website platform whose AI agents build, host and manage…
- AgentUI — Managed AI app builder for operations teams that generates and hosts…
- Aider — Open source, model agnostic terminal coding agent that edits your…
- Amp — Amp is a coding agent from Amp Frontier Corporation that runs each…
- Anthropic Claude Code — Anthropic's agentic coding system across terminal, desktop, IDE, web…
Alternatives to Blink
The closest documented capability profiles to Blink among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Hoplite11.5 / 14Fuller documented coverage on Workflow Orchestration and Observability & Auditability
- Anything11.0 / 14Fuller documented coverage on Workflow Orchestration and Observability & Auditability
- Caffeine11.0 / 14Fuller documented coverage on Workflow Orchestration and Human Oversight & Guardrails
- Choicely9.0 / 14Fuller documented coverage on Deployment & Data Residency
- Cline12.0 / 14Fuller documented coverage on Workflow Orchestration and Human Oversight & Guardrails
- Codebuff9.0 / 14Fuller documented coverage on Workflow Orchestration
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded