OpenSecureAI Prompt Firewall evaluates text before it reaches an LLM and applies a policy to allow, flag, or block it. Its separate detection engines look for prompt injection, secrets, and personally identifiable information. Under the stated policy, injection or secrets trigger a block, while PII is redacted and flagged. The live demonstration processes text in the browser, and the core engine can also be used as middleware on model inputs or outputs. Developers can use the open-source, dependency-free npm package or CLI in applications and CI. The CLI reads files or standard input and can return a nonzero exit code when findings reach a chosen threshold. An API key enables hosted detections for evasion methods, indirect injection, tool abuse, multilingual overrides, and de-obfuscation. The LLM Gateway supports OpenAI, Anthropic, xAI, and Groq using bring-your-own-key operation; OpenSecureAI says provider keys are not stored or logged. The Free plan is 0.00 USD per month, and Pro is 49.00 USD per month. Team pricing is custom.
Who it is for
It is aimed at AI application teams deploying LLM features and developers building agents. The CLI and npm package also suit teams adding text checks to applications or CI.
What is good
- Policy combines injection, secret, and PII checks
- CLI can scan files or standard input
- Core engine is open source and dependency-free
- Free plan includes 2,000 API requests per month
- Supports OpenAI, Anthropic, xAI, and Groq via BYOK
What to know first
- Free plan caps usage at 2,000 API requests monthly
- Hosted enhanced detections require an API key
- Team pricing is custom
- Team SSO and SLA are planned, not listed as available
Verdict
Prompt Firewall combines text detection with configurable allow, flag, and block outcomes, and offers both browser and developer tools. Compare the Free and Pro request limits with your needs; Team pricing is custom.
Get started with OpenSecureAI Prompt Firewall
- Open the Prompt Firewall website.
- Use the browser-based demonstration to evaluate text in the client.
- For application or CI use, install the free @opensecureai/firewall npm package or use its CLI.
- Choose the Free plan or Pro at $49/month for the stated API allowances and features.
- Supply an API key to access hosted detections and LLM Gateway features.
What the free plan stops at
Free includes 2,000 API requests per month and 30 requests per minute per key. Hosted AI remediation and LLM Gateway completions are included with Pro, which costs $49/month and allows 50,000 requests monthly at 120 requests per minute per key.
Questions about OpenSecureAI Prompt Firewall
Is there a free plan?
Yes. Free costs $0/month and includes 2,000 API requests per month, 30 requests per minute per key, in-browser tools and npm packages, scan history synced to an account, a BYOK LLM Gateway, and BYOK AI remediation.
How much does Pro cost?
Pro costs $49/month. It includes 50,000 API requests per month, 120 requests per minute per key, hosted AI remediation and LLM Gateway completions, and priority email support.
Which platforms does it support?
The listed platforms are self-hosted and web. The core engine is also available as a TypeScript npm package and CLI.
Is the core open source?
Yes. The core engine and npm packages are open source and dependency-free.
Which model providers does the LLM Gateway support?
It supports OpenAI, Anthropic, xAI, and Groq with bring-your-own-key operation. OpenSecureAI says gateway provider keys are never stored or logged.
What does Team cost?
Team is billed at a custom price. The listed plan includes 250,000 API requests per month and 300 requests per minute per key; team seats, SSO, custom rules, and SLA are marked planned.
OpenSecureAI Prompt Firewall plans and pricing
All plansCompared on AI guardrail software
- Free plan
- Yes
- Paid from
- $49/mo
- Deployment
- hybrid
- Prompt injection defense
- Yes
- PII detection
- Yes
- Jailbreak detection
- Yes
- Custom policies
- Yes
- SDK languages
- TypeScript
