Pricing
Pay for what you intercept.
No per-seat fees. No data egress costs. Start free, scale when your AI agents do.
Hacker
$0
For indie devs exploring AI security.
5,000 intercepts / month
- Prompt, command & diff scanning
- Built-in secret detection (AWS, GitHub, PII...)
- MAS-TRM risk scoring
- 3 custom regex rules
- 10 MCP Copilot requests / month
- 7-day audit log retention
- 1 GitHub repo integration
- Community support
Pro Developer
$20/mo
For teams shipping AI-powered products.
150,000 intercepts / month
- Everything in Hacker
- Unlimited custom interceptor rules
- Regex tester with inline feedback
- 50 MCP Copilot requests / month
- 30-day audit log retention
- Incident triage & block records
- 5 GitHub repo integrations
- Multi-seat team access
- Priority email support
Business
Popular$99/mo
For companies running AI at scale.
1,000,000 intercepts / month
- Everything in Pro
- 200 MCP Copilot requests / month
- 90-day audit log retention
- Unlimited GitHub repo integrations
- Dedicated Slack support channel
Enterprise
Custom
For regulated industries and large teams.
Unlimited
- Everything in Business
- Dedicated single-tenant deployment
- Self-hosted VPC option
- Custom SLA with 99.99% uptime
- 500 MCP Copilot requests / month
- 1-year log retention
- SSO (OpenID Connect) & SCIM provisioning
- White-glove onboarding
Need more intercepts mid-cycle?
API credits: $10 = 10,000 requests ($0.001 each). Minimum $10.
More AI Copilot interactions?
MCP credits: $5 = 100 requests ($0.05 each). Minimum $5.
02 / Included
In every plan, from day one.
Prompt scanning
Secrets, PII, connection strings and private keys in LLM prompts.
Command scanning
Destructive deletes, privilege escalation, raw disk writes and unsafe pipelines.
Diff scanning
Credentials, tokens and webhooks in AI-generated diffs, before commit.
MAS-TRM risk scoring
Every finding scored on a Likelihood × Impact matrix, Low to Critical.
Tamper-evident audit trail
Every blocked action recorded in a hash-chained, searchable log.
Secrets never stored
Allowed payloads are not kept. Blocked records are stored with secrets masked.
03 / FAQ
Questions, answered.
What does BLAZLE actually intercept?
Three surfaces: LLM prompts (secrets, PII, injections), shell commands (destructive ops, privilege escalation, unsafe pipelines) and git diffs (hardcoded credentials and tokens).
What counts as one intercept?
Each call to /intercept/prompt, /intercept/command or /intercept/diff counts as one request against your monthly quota.
How is risk scored?
Every finding is mapped to a Likelihood × Impact matrix derived from MAS-TRM (Monetary Authority of Singapore Technology Risk Management guidelines). Each finding is rated Low to Critical, and you choose the rating at which requests are blocked.
Is my payload stored?
Allowed payloads are not stored, and detection never sends your payload to a third-party AI service. Blocked requests are kept as investigation records with detected secrets masked, for your plan's retention period.
What happens when I reach my quota?
You are notified at 80% and 100% of your monthly quota. Top up with pay-as-you-go credits at any time from your dashboard, or upgrade your plan to keep every request protected.
Can I self-host BLAZLE?
Enterprise customers can deploy BLAZLE within their own VPC or on-premise infrastructure. Talk to us to discuss.
Start protecting your agents today.
Free forever on the Hacker tier. No credit card required.