Devin, built by Cognition, is an agentic software engineering product spanning Devin Desktop, a CLI, Devin Cloud agents, DeepWiki and the Devin API, aimed at multi-repo engineering work such as migrations, PR review, incident triage and scheduled chores. Its pricing page lists Free at $0 with "a light quota to code with agents", limited model availability, unlimited inline edits and unlimited Tab completions, then Pro at $20/month, Max at $200/month for significantly higher quotas, Teams at $80/month for the team plan plus $40/month per full dev seat, and Enterprise by contact. Paid plans come with a usage allowance that refreshes daily and weekly, and usage beyond the allowance is purchased and consumed at API pricing.
Paste an existing Devin API key from an authenticated Devin session. Key export availability and steps vary by Devin version and account.
// pros
- Free at $0 includes unlimited inline edits and unlimited Tab completions in Devin Desktop alongside a light agent quota.
- Pro at $20/month unlocks full model availability across OpenAI, Claude and Gemini frontier models, plus cloud agents and deferred extra-usage purchase at API pricing.
- Included allowances on paid plans refresh on daily and weekly cycles rather than resetting once a month.
- Teams at $80/month plus $40/month per full dev seat adds unlimited team members, shared collaboration, centralized billing, an admin dashboard with analytics and priority support.
- SWE-2 and leading open source models are free in Devin Desktop and CLI through October 10, 2026, and the product integrates with GitHub, GitLab, Bitbucket, Slack, Teams, Linear and Jira.
// cons
- The Free plan's agent allowance is published only as a "light quota" - no message count, agent minutes or session cap appears on the pricing page.
- Max at $200/month and Teams at $80/month plus $40 per seat make the higher tiers expensive relative to single-seat competitors.
- Unlimited inline edits and Tab completions apply to the local desktop surfaces; agent work in Devin Cloud is quota-limited on every plan.
- Free SWE-2 access in Devin Desktop and CLI is explicitly time-limited to October 10, 2026.
Use the Free plan to evaluate Devin Desktop's Tab and inline editing before paying, then take Pro at $20/month if you want frontier models and cloud agents. Because free agent capacity is not quantified, keep a free backup such as Copilot Free or Zed Personal for everyday editing so you are not blocked at the quota edge.
imported analysis — independent third party, not Uprouter editorial · verify before relying on it
Value taken from the provider’s own published free-tier terms, expressed in USD.
note: Devin Free is $0 with a light agent quota, limited model availability, unlimited inline edits and unlimited Tab completions (devin.ai/pricing, checked 2026-09-16).
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Max | subscription | $200.00/mo | — | — | USD 200/mo: high-usage tier. |
| Teams | subscription | $80.00/mo | — | — | USD 80/mo base plus USD 40 per developer seat. |
| Enterprise | subscription | — | — | — | Custom enterprise pricing. |
| Free (SWE-2 + open-source models in Desktop/CLI) | free | — | — | — | Free use of SWE-2 and leading open source models in Devin Desktop and CLI through Oct 10, 2026. |
| Teams (base) | subscription | $80.00/mo | — | — | $80/month for the team plan plus $40/month per full dev seat; admin dashboard with analytics. Per-seat price: $40. |
| Free | free | — | — | — | Light usage quota; unlimited tab completions. |
| Pro | subscription | $20.00/mo | — | — | USD 20/mo: frontier models, extra usage at API pricing, cloud agents. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Claude Sonnet 4.5 | — | — | 1M |
| Claude Opus 4.5 | — | — | 200k |
| GPT-5.5 Pro | — | — | 1.1M |
| Gemini 3.8 Flash | — | — | 1.0M |
| DeepSeek V3.2 | — | — | 164k |
| kimi-k3 | — | — | 1.0M |
| glm-5.3 | — | — | 1.3M |
| SWE-2 | — | — | — |
| SWE-2 | — | — | — |
$ Does Devin Desktop have a free tier? #
Yes — Devin Desktop offers a free tier that we value at roughly $0 in free credits. Always confirm current limits on Devin Desktop's official pricing page — free tiers change without notice.
$ How much does Devin Desktop cost per 1M tokens? #
Devin Desktop does not publish simple per-1M-token pricing (it may bill per request, per output, or via a subscription plan). Check their official pricing page for exact figures.
$ Is Devin Desktop safe to use? #
Uprouter rates Devin Desktop as low risk. Medium-to-high risk on the free tier because Cognition publishes only qualitative limits - "light quota" and "limited model availability" - rather than numbers, so free-tier overage behaviour is undocumented on the pricing page. On paid plans, cost per message varies with model, task size and reasoning depth, and free SWE-2 access in the desktop and CLI carries an explicit end date of October 10, 2026. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
$ Can I use Devin Desktop through Uprouter Connect? #
Devin Desktop is not marked Connect-compatible in our catalog yet. You can still use their API directly, or request compatibility via /submit.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets #
price_history
No recorded changes yet.
live_status
current: unknown No probes recorded yet.
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
Medium-to-high risk on the free tier because Cognition publishes only qualitative limits - "light quota" and "limited model availability" - rather than numbers, so free-tier overage behaviour is undocumented on the pricing page. On paid plans, cost per message varies with model, task size and reasoning depth, and free SWE-2 access in the desktop and CLI carries an explicit end date of October 10, 2026.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
curl https://app.devin.ai/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-sonnet-4.5",
"messages": [{ "role": "user", "content": "Hello" }]
}'
Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
GitHub Copilotfree $0in from Free/1MLow risk
GitLab Duo PATfree $0in from $0.0000/1MLow risk
Kimifree $2.10 est.pricing n/aconnectLow risk
Amazon Qfree tier (n/q)in from $0.035/1MLow risk
Ranked by neutral similarity signals only — live status, Connect compatibility, free-tier shape and free-credit proximity. Commercial relationships never influence this list.