Promptfoo helps developers and enterprises evaluate prompts and test AI applications for security risks. It compares prompt outputs across multiple models in a web view. Its red-team testing simulates users and looks for prompt injections, jailbreaks, data leaks, business rule violations and unsafe agent tool use. The getting-started guide lists more than 60 providers, including OpenAI, Anthropic, Google and local models such as Ollama. Integrations include CI systems such as GitHub Actions, GitLab CI, Jenkins, Azure Pipelines, CircleCI and Bitbucket Pipelines, as well as Splunk, Burp Suite, Google Sheets and MCP. Promptfoo can be installed through npm, npx or Homebrew, and requires Node.js 22.22.0 or newer; Node.js 24 LTS is recommended. The free Community plan includes all LLM evaluation features and 10k red-team probes per month, and can run locally or be self-hosted. Enterprise includes managed cloud deployment, while On-Premise is deployed on customer infrastructure. Promptfoo says it is based in San Francisco, is part of OpenAI and remains open source.
Who it is for
It suits developers and enterprises evaluating prompts across models or checking AI applications for security risks. Community is for those who can run locally or self-host; organizations needing managed cloud or on-premise deployment have separate plans.
What is good
- Lists more than 60 model providers.
- Compares outputs across multiple models.
- Community includes 10k red-team probes per month.
- Offers local, self-hosted, managed-cloud and on-premise options.
- Integrates with CI systems and security tools.
What to know first
- Requires Node.js 22.22.0 or newer.
- Community is limited to 10k red-team probes per month.
- Enterprise and On-Premise pricing is custom and not listed.
Verdict
Promptfoo combines prompt evaluation with red-team testing and a broad provider and integration list. The free Community plan has a monthly probe limit; deployment and support needs may point to custom-priced plans.
Promptfoo plans and pricing
All plansCompared on AI LLM evaluation tools
- Free plan
- Yes
