Pricing
Priced per user, with no annual contract.
Every plan is self-serve and monthly. Model usage is pay as you go, or bring your own keys.
Free
$0 forever
One gateway for every model, with logs and a tamper-evident record built in.
Get started- Multi-provider routing: one base URL for OpenAI, Anthropic, and more
- 20,000 recorded requests per month
- 30-day log retention, 90-day metrics retention
- Request-level logs: cost, tokens, and latency across the workspace
- Basic compression on every request
- Immutable audit trail: every message fingerprinted to Constellation Digital Evidence
- Conversation threading: follow agent runs end-to-end
- Gate Connect desktop app for no-code setup
Most popular
Pro
$20 per user / month
The full defense layer: screening, redaction, caps, and savings on every request.
Start free trial- Everything in Free, plus:
- 200,000 recorded requests per month
- 90-day log retention, 180-day metrics retention
- Prompt injection scanning: block or flag before tokens reach the model
- PII, PHI, and credential redaction before the response returns
- Spend, token, and rate limits at the org, project, or key level
- Advanced compression: 20%+ saved per message, by sending repeated content once and injecting cache markers
Enterprise
Custom
For larger teams with deployment, security, and procurement requirements.
Contact us- Everything in Pro, plus:
- Custom retention periods and volume pricing
- Custom security policies
- Private cloud deployment and VPC hosting
- Data isolation and data export
- Dedicated onboarding and priority support
- Procurement: security review, DPA, invoicing
Pay as you go
Usage bills separately from your plan.
Model usage and security scans draw on a prepaid balance, on every plan including Free. Top up by card, or turn on auto top-up.
Models
Pay per token.
Run any model in the catalog with one Gate API key. No provider account needed.
- One bill across every provider
- Your live balance in the dashboard
Security Scan API
Pay per scanned token.
Check any text for prompt injection, PII, PHI, and credentials.
- Prompt injection
- $1.00/ 1M tokens
- PII, PHI, and credentials
- $0.50/ 1M tokens
FAQ
Common questions
Do I need a credit card to start?
No. The Free plan is free forever and doesn't ask for a card. You only add payment details when you upgrade to Pro or add credit for model usage or security scans.
How is model usage billed?
Pay as you go per token. If you'd rather use your existing OpenAI or Anthropic account, bring your own keys and pay your provider directly.
Do security scans need a paid plan?
No. The Security Scan API bills per scanned token on every plan, including Free. Screening of traffic through Gate's gateway is included in Pro at no per-request charge.
What happens when my balance runs out?
Requests on Gate's keys and security scans stop until you add credit, so you never spend more than you've paid. Auto top-up refills the balance before it runs out.
Can I get a refund on unused credit?
Yes. Within 24 hours of a top-up, refund the unspent credit from the billing page. The processing fee isn't refunded. After 24 hours, contact support.
Can I use my Claude or ChatGPT subscription?
Yes. Gate sits in front of the tools you already use, so you can keep your Claude Code or ChatGPT subscription, or run hundreds of models directly through Gate on pay-as-you-go.
How do spend caps work?
On Pro you can cap spend, tokens, and request rate at the organization, project, or API-key level. When an agent hits its cap, Gate stops the requests instead of your credit card.
Can I cancel anytime?
Yes. Plans are monthly and self-serve. Downgrade to Free from the billing page whenever you want; your workspace keeps routing, logs, and the audit trail, and nothing is deleted.