> Cursor API
Cursor is an AI code editor sold on self-serve plans: Hobby is free, the $20/month individual tier (listed as Individual on the pricing page and as Pro in the docs) adds extended Agent limits and frontier models, Pro Plus is $60/month, Ultra is $200/month, and Teams is $40/user/month Standard or $120/user/month Premium with Enterprise as custom. Hobby requires no credit card and lists limited Agent requests and access to Composer. Cursor states there are two usage pools - Cursor Models for Grok 4.6, Grok 4.5 and Composer 2.5, and Other Models for third-party models billed at API price - and that Teams and Enterprise add a $0.25 per million token Cursor Token Rate on third-party model requests.
// pros
- Hobby is free with no credit card and includes access to Composer plus limited Agent requests.
- The $20/month tier bundles extended Agent limits, frontier model access, MCPs, skills, hooks, cloud agents and Bugbot on usage-based billing for one seat price.
- Cursor Models pricing is published (Grok 4.6 and Grok 4.5 at $2 input / $6 output per million tokens, Composer 2.5 at $0.50 / $2.50), while third-party models bill at their own API rates.
- Teams Standard at $40/user/month adds centralized billing, a team marketplace for internal rules and plugins, shared-context cloud agents, Bugbot code reviews, usage analytics and SAML/OIDC SSO, with a $120/user/month Premium seat that adds 5x Standard Agent limits.
- On-demand usage continues past the included pool at the same API rates with no quality downgrade, and a Cursor Start plan at 649 INR/month exists for developers in India.
// cons
- The free Hobby tier's Agent allowance is published only as "limited" - no numeric cap appears on the pricing page.
- Naming is inconsistent between surfaces: the pricing page shows Hobby/Individual/Teams/Enterprise while the pricing FAQ and docs refer to Pro, Pro Plus and Ultra, which makes tier matching error-prone.
- Bugbot on the $20 tier is usage-based, regional data residency adds a 10% uplift on model pricing, and Teams/Enterprise third-party requests carry a $0.25 per million token Cursor Token Rate on top of API pricing.
- Privacy mode must be enabled by the user or a team admin to guarantee code data is not used for training by Cursor or its model providers.
Start on free Hobby to test whether Cursor's Composer-style editing fits your workflow, then take the $20/month individual plan when Agent runs are routine, moving to Ultra only for multiple parallel agents. Cursor is also the plan most worth pricing against a Copilot Pro seat before committing, and Cursor notes that subscriptions bought from resellers may be suspended.
written by Mike Fleming, Uprouter editorial · verified against official sources September 16, 2026
Value taken from the provider’s own published free-tier terms, expressed in USD.
note: Cursor Hobby is free with no credit card required, limited Agent requests and access to Composer (cursor.com/pricing, checked 2026-09-16).
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Pay-as-you-go | payg | — | $0.0000 | $0.0000 | Cheapest tracked model rate (OpenRouter-normalized). |
| On-demand Overage | payg | — | $0.500 | $1.50 | Billed in arrears for usage beyond the included plan quota. |
| Hobby | free | — | — | — | Free tier: limited agent requests, Composer access, no credit card required. |
| Pro+ | subscription | $60.00/mo | — | — | USD 60/mo: 3x Pro usage. |
| Ultra | subscription | $200.00/mo | — | — | USD 200/mo: 20x Pro usage. |
| Start (India) | subscription | $20.50/mo | — | — | India-only plan at Rs 649/mo (approx USD 20.5). |
| Teams | subscription | $40.00/mo | — | — | USD 40 per user/mo (enterprise USD 120); shared usage pool. |
| On-Demand usage | payg | — | — | — | Pay-as-you-go at upstream model API rates for models in the Other Models pool. |
| Pro | subscription | $20.00/mo | — | — | USD 20/mo: expanded agent requests plus usage; extra usage at model API rates. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| gpt-3.5-turbo | $0.0000 | $0.0000 | 16k |
| Anthropic: Claude 3.5 Sonnet | $0.0000 | $0.0000 | 200k |
| GPT-4o | $0.0000 | $0.0000 | 128k |
| GPT-5.5 Pro | — | — | 1.1M |
| GPT-5.6 Luna Pro | — | — | 1.1M |
| GPT-5.6 Terra Pro | — | — | 1.1M |
| GPT-5.6 Sol Pro | — | — | 1.1M |
| GPT-6 Astra | — | — | 1.1M |
| GPT-5.1 | — | — | 400k |
| Claude Fable 5.1 | — | — | 1M |
| Claude Opus 4.5 | — | — | 200k |
| Claude Sonnet 4.5 | — | — | 1M |
| Claude Haiku 4.5 | — | — | 200k |
| Gemini 3.8 Flash | — | — | 1.0M |
$ Does Cursor API have a free tier?
Yes — Cursor API offers a free tier that we value at roughly $0 in free credits. Always confirm current limits on Cursor API's official pricing page — free tiers change without notice.
$ How much does Cursor API cost per 1M tokens?
The cheapest model we track at Cursor API is $0.0000 per 1M input tokens and $0.0000 per 1M output tokens. This is normalized from Cursor API's published pricing — verify with the provider before purchasing, since prices change frequently.
$ Is Cursor API safe to use?
Uprouter rates Cursor API as low risk. Medium risk. The free tier is a real $0 plan but its Agent allowance is unpublished, so capacity is unpredictable until you upgrade, and paid usage can spill into on-demand charges billed at API rates. Cursor states subscriptions are sold only through cursor.com and that accounts bought elsewhere may be suspended, and training protection requires privacy mode to be switched on. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
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: unknownNo 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 risk. The free tier is a real $0 plan but its Agent allowance is unpublished, so capacity is unpredictable until you upgrade, and paid usage can spill into on-demand charges billed at API rates. Cursor states subscriptions are sold only through cursor.com and that accounts bought elsewhere may be suspended, and training protection requires privacy mode to be switched on.
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
# Cursor API's own API — get a key from their dashboard
curl https://cursor.com/dashboard/api/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-3-5-sonnet",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.