# Devin > Source: https://agentsindex.ai/devin Autonomous software engineering agent from Cognition that plans, codes, tests in its own VM and opens PRs. Devin is Cognition's autonomous coding agent that works in cloud VMs, a desktop app and a CLI, routing tasks across frontier models. It maps a codebase, writes and tests code in its own browser, reviews changes and opens pull requests. - Best for: Engineering teams who need an AI agent to handle migrations, reviews, and ticketed work. - Look elsewhere if: - you need the full API on every plan Starting price Free From [devin.ai/pricing](https://devin.ai/pricing), checked 6 November 2026 - MCP server Partly - API Partly - Open source Partly - Self-host Not stated [Docs](https://docs.devin.ai/) What we checked - Pages last read: 6 November 2026 - Facts checked: 5 facts From 5 sources, read 27 October 2026 - AI answers: Named in 1 of 62 Buyer questions, our November check [How we check](https://agentsindex.ai/methodology) [Editorial policy](https://agentsindex.ai/editorial-policy#not-for-sale) [Visit Devin](https://agentsindex.ai/go/devin) [Compare](https://agentsindex.ai/compare?cat=coding-agents&products=devin) ## At a glance - Category: [Coding agents](https://agentsindex.ai/categories/coding-agents) - Tags: Freemium, Free trial ### For developers - Runs: Cloud ### Security - Compliance: SOC 2 Type II, ISO/IEC 27001 ## What Devin actually is Devin isn't an editor extension — it's a cloud-hosted agent with its own VM (shell, browser, and embedded IDE) that you hand a ticket to, and it plans, edits, runs tests, and opens a PR largely unsupervised. You can watch or take over live. It ships as a web app, a desktop app, a CLI, and a Slack/Teams/Linear/Jira-triggered "automations" layer that can start work from an event without anyone opening a chat. That architecture is the main differentiator from IDE copilots: it's built for delegating whole tickets, not completing the next line. ## Where it's strongest: migrations, backlog, and security triage Cognition (Devin's maker) markets it specifically for code migrations and modernization (language ports, framework upgrades, monorepo splits), routine engineering work (PR review, bug repro, test writing), and — as of the security product launch — vulnerability discovery. On Cognition's own published benchmark, Devin Security Swarm found 36 of 50 real-world GitHub Security Advisory vulnerabilities (72% recall) at $90.23 per run, which it says beats Claude Security (68% recall, $131.87) and Codex Security (48%, $118.20) on both axes; Cursor Security scored lower recall (26%) but far cheaper ($4.60) ([devin.ai/security](https://devin.ai/security), [devin.ai/blog/security-swarm-eval](https://devin.ai/blog/security-swarm-eval)). These are vendor-run, vendor-published numbers on a benchmark Cognition built — no independent lab has replicated them — but the methodology (published GHSA vulnerabilities, cost-per-finding, exploit validation before surfacing) is more transparent than most vendor security claims we see. ## Coding model and independent benchmarking Devin runs on Cognition's own SWE-2 model (released 10 September 2026), which the company says scores 50.0% on its own FrontierCode 1.1 benchmark — within a point of Fable 5.1 and beating Grok 4.6, at a fraction of the cost of larger frontier models like GPT-6 Astra ([cognition.com/blog/swe-2](https://cognition.com/blog/swe-2)). FrontierCode is Cognition's own benchmark, not an independent one; we could not find Devin or SWE-2 on a third-party leaderboard we could verify (Terminal-Bench's public leaderboard table rendered empty via automated fetch, and we could not confirm a listing there). Treat all model-quality comparisons above as vendor-reported until an independent benchmark confirms them. ## Pricing Free tier ($0) gives a light usage quota, limited model access, and unlimited inline edits/Tab completion. Pro is $20/month with full model access (OpenAI, Claude, Gemini, and others) and cloud agent access; Max is $200/month for "significantly higher" quotas. Teams costs $80/month plus $40/month per full seat. Enterprise is quote-only and adds SSO, VPC deployment, and dedicated support. All paid tiers meter usage by an internal quota that resets daily/weekly; going over it bills extra usage at API cost, and Cognition doesn't publish that per-model rate card on the pricing page ([devin.ai/pricing](https://devin.ai/pricing), verified 19 September 2026). ## Company and funding Cognition (Devin's maker), founded 2024, closed a Series E on 2026-09-08: over $2B raised at a $48B valuation, led by Andreessen Horowitz and Accel, up from a $26B valuation in its May 2026 Series D. Cognition says run-rate revenue grew from $492M to almost $900M over that period, and names NVIDIA, GE Aerospace, Citi, Mercedes-Benz, and Modal as customers — these are vendor-stated figures and customer names, not independently confirmed ([cognition.com/blog/series-e](https://cognition.com/blog/series-e)). The company has also expanded into an independent "agent lab" model, building its own SWE-2 coding model rather than relying solely on third-party LLMs, and has opened offices in Washington D.C., Tokyo, Singapore, London, São Paulo, and Madrid in the past year per the same post. ## Security and compliance posture Cognition publishes a SafeBase-hosted Trust Center listing SOC 2 Type 2, ISO/IEC 27001:2022, and CCPA compliance, plus a Data Processing Addendum, pentest report, and SOC 2 report — the underlying documents require an NDA click-through to view, which is standard for this format ([trust.cognition.ai](https://trust.cognition.ai/)). Enterprise plans add SAML/OIDC SSO and VPC deployment. A separate status page (devinstatus.com) tracks incidents with an Atom feed of past outages, though incident titles aren't populated in the feed we could fetch, so we can't characterize Devin's reliability history from it directly. ## Release pace Devin's public release notes show near-daily shipped changes — new integrations (PagerDuty, Datadog MCP, 21 new one-click OAuth connectors), UI and workflow changes, and security-review features — through at least September 16, 2026, the week this listing was checked ([docs.devin.ai/release-notes/overview](https://docs.devin.ai/release-notes/overview)). This is an actively developed product, not a stalled one. Our take Check whether the workflow you need sits behind the Pro quota or the Teams/Enterprise controls. Pro includes Devin usage quota plus Slack, Linear, and MCP integrations, while Enterprise adds SAML/OIDC SSO and centralized admin controls. ## How much does Devin cost? Prices excluding tax, as Devin publishes them. - Free · Free - Limited Devin usage - Devin Review - DeepWiki - Pro · $20/month - Everything in Free - Devin usage quota - Pay-as-you-go for usage past quota - Slack, Linear, MCP integrations - Max · $200/month - Everything in Pro - Increased Devin usage quota - Teams · $80/month - Everything in Pro - Unlimited team members - Share and collaborate - Centralized billing - Admin dashboard with analytics - Enterprise · Custom pricing - Everything in Teams - SAML/OIDC SSO - Centralized enterprise admin controls - Dedicated account team - Custom terms [![Devin](https://agentsindex.ai/img/1024/screenshots/devin/pricing.webp)](https://agentsindex.ai/img/1920/screenshots/devin/pricing.webp) Pricing page, captured 24 October 2026 [devin.ai/pricing](https://devin.ai/pricing), checked 6 November 2026 ### All plans and limits | Plan | Price | Main limits | | --- | --- | --- | | Free | $0 a month | Members: 1; Agent quota: Light quota to code with agents; Inline edits: Unlimited | | Pro | $20 a month | Members: 1 | | Teams | $80 per team plan a month | Concurrent sessions in Free mode: 2 per user; Up to 100 users | | Max | $200 a month | Members: 1; Significantly higher quotas | | Enterprise | Price on request | None stated | Read 12 November 2026 from [devin.ai/pricing](https://devin.ai/pricing). ## For AI agents - MCP server: Partly - API: Partly [Developer docs](https://docs.devin.ai/) ## What we checked on Devin Yes Partly No What it costs to start Yes ### What the price counts Priced as flat monthly plans with usage quotas: $20 Pro and $200 Max for individuals, while Teams adds a per-seat charge on top of a platform fee and Enterprise is quote-only. > Teams $80/month for team plan + $40/mo per full dev seat Plan cards, Team plans section, Teams card price line [devin.ai/pricing](https://devin.ai/pricing) Checked 27 October 2026 What it costs to start Yes ### Free tier A standing $0 Free plan lets you download and code with agents on a light quota without a sales call, but model availability is limited and cloud agents only arrive on the $20 Pro plan. > The Free plan includes a light quota to code with agents, limited model availability, unlimited inline edits, and unlimited Tab completions. Frequently Asked Questions, 'What is included in the Free plan?'; Free plan card [devin.ai/pricing](https://devin.ai/pricing) Checked 24 October 2026 How you build with it Partly ### Public API The Devin REST API (service users, RBAC, sessions, playbooks, audit logs) is crossed out for Free and ticked from Pro upward in the plan comparison. > The Devin API enables you to integrate Devin into your applications, automate workflows, and build powerful tools. API Overview, opening paragraph [docs.devin.ai/api-reference/overview](https://docs.devin.ai/api-reference/overview) Checked 3 September 2026 How you build with it Partly ### MCP server Devin Desktop is an MCP client that consumes servers with per-tool approval; the server another agent can query is the Devin platform's, at mcp.devin.ai, not the desktop session. > Beyond repository documentation and search, it gives any MCP-compatible AI agent or IDE full access to session management, playbooks, knowledge, and… Opening paragraph [docs.devin.ai/work-with-devin/devin-mcp](https://docs.devin.ai/work-with-devin/devin-mcp) Checked 3 September 2026 How you build with it Partly ### Open source Only the Outposts Kubernetes orchestration operator is published as open source; no source distribution is documented for Devin itself. > deploy devin-outpost-k8s — our open-source operator that runs the loop on any Kubernetes cluster Devin Outposts overview, Orchestration paragraph [docs.devin.ai/cloud/outposts/overview](https://docs.devin.ai/cloud/outposts/overview) Checked 2 September 2026 ## Devin alternatives - [Hyper](https://agentsindex.ai/hyper) · The team behind Hyper runs this listing · Autonomous engineering agent that tests each delivery in a real browser on its servers and ships it with evidence. · Free, then $20 a month Checked 11 Nov · Featured Freemium Free trial · [Visit](https://agentsindex.ai/go/hyper) - MCP server - API - Open source - Self-host - Devin and Hyper | Devin | Free, then $20 a month | 27 Oct | | --- | --- | --- | | [Hyper](https://agentsindex.ai/hyper) | Free, then $20 a month | 11 Nov | ## Where we've written about Devin - [Hyper review (2026): an autonomous coding agent that ships verified pull requests](https://agentsindex.ai/blog/hyper-review-autonomous-coding-agent) - [AI coding agents compared: what each one is actually good at](https://agentsindex.ai/blog/ai-coding-agents-what-each-is-good-at) ## Questions about Devin - How much does Devin cost?: Devin has a free plan. Its paid plans include Pro at $20 a month, Teams at $80 per team plan a month and Max at $200 a month. From devin.ai/pricing, checked 6 November 2026. - Does Devin have an API or an MCP server?: It has a limited API. It has a limited MCP server. - Is Devin open source, and can you host it yourself?: Part of it is open source. - What have we checked on Devin?: 5 facts, under these headings: What it costs to start, how you build with it. - How do we check Devin?: We hold 5 facts on Devin, quoted from 5 pages. Facts last checked 27 October 2026. Price last checked 6 November 2026. [How we check every listing](https://agentsindex.ai/methodology) ## Sources and changes Last changed 6 November 2026 Sources 5 - Read 6 November 2026 · [devin.ai](https://devin.ai/pricing) /pricing - Read 6 November 2026 · [devin.ai](https://devin.ai/) / - Read 3 September 2026 · [docs.devin.ai](https://docs.devin.ai/api-reference/overview) /api-reference/overview - Read 2 September 2026 · [docs.devin.ai](https://docs.devin.ai/cloud/outposts/overview) /cloud/outposts/overview - Read 3 September 2026 · [docs.devin.ai](https://docs.devin.ai/work-with-devin/devin-mcp) /work-with-devin/devin-mcp ## Similar to Devin [See all in Coding agents](https://agentsindex.ai/categories/coding-agents) - [ERIUS PHONE](https://agentsindex.ai/eriusphone) A dedicated virtual Android phone per AI agent, with Google Play apps and sign-ins that persist between sessions. From about $45 a month - [TinyFish](https://agentsindex.ai/tinyfish) One web layer for agents: free search and fetch, plus hosted browsers and goal-driven web automation. Free plan, then $0.002 per minute - [UI Discovery](https://agentsindex.ai/uidiscovery) Library of real website and app UI sections, queryable by AI assistants over MCP and a REST API. Free plan, then $15 a month - [ClineFlow](https://agentsindex.ai/clineflow) Git-native project memory and handoffs for coding agents. Free plan ## From our research [All research](https://agentsindex.ai/blog) - [Comparison](https://agentsindex.ai/blog/daytona-vs-e2b-vs-modal) 16 Oct 2026 Daytona vs E2B vs Modal: which sandbox for agent code? Daytona, E2B and Modal compared on sandbox pricing, concurrency, GPU support and open-source status, plus why Daytona's flagship repo is now archived. - [Buyer's guide](https://agentsindex.ai/blog/erius-phone-ai-agent-android-device) 9 Oct 2026 ERIUS PHONE review (2026): pricing, pros and cons ERIUS PHONE rents AI agents real cloud Android phones they drive by API, priced monthly per phone in euros, but it offers no webhooks. - [Buyer's guide](https://agentsindex.ai/blog/superbot-pricing-use-cases-alternatives) 22 Oct 2026 superbot review (2026): pricing, pros and cons, alternatives superbot runs errands, admin and scheduled tasks on your computer, free to start with paid credit plans, for busy people, but promises no uptime. ## Is this yours? Claim it free, then see who reads this page and carry the verified owner mark. You confirm it with an email at devin.ai. [Claim this listing](https://agentsindex.ai/claim/devin?from=owner-line) [Get Featured](https://agentsindex.ai/claim/devin?from=owner-line&next=featured) [Report an error](mailto:hello@agentsindex.ai?subject=Report%20an%20error%3A%20Devin%20(devin)&body=What%20is%20wrong%20on%20the%20page%2C%20and%20where%20on%20the%20product) if a fact is wrong.