AI Tools
Promptfoo
Promptfoo: preços, capacidades, atualizações e alternativas, lidos nas páginas do próprio desenvolvedor.

Em inglês
Key facts
- Price
- Price on request Read on promptfoo.dev
- Free plan
- Yes Read on promptfoo.dev
- Platforms
- Web · CLI · VS Code · API
- API
- Yes
- Open source
- Yes Read on github.com
- Certifications
- SOC 2 Type II · ISO 27001 Read on trust.promptfoo.dev
- Latest version
- 0.126.0 Read on github.com
- Last update
- 3 Mar 2026 Read on promptfoo.dev
Promptfoo helps developers evaluate prompts, models, agents, and RAG pipelines using test cases and automated assertions. It can compare outputs, run red-team tests for issues such as prompt injection and data leaks, and integrate checks into development workflows.
It is available as an open-source CLI and web viewer, with enterprise features for teams. The Community plan is free and includes up to 10k red-team probes per month; Enterprise and On-Premise pricing is custom. Model-provider credentials may be needed to run tests.
- Category
- Developer Tools
- Read from the maker’s pages
- 2026-11-18
Company
Features
- Evaluate prompts and models against configured test cases and assertions
- Compare outputs from multiple model providers
- Run red-team scans for prompt injection, jailbreaks, and data leaks
- Test agents, RAG pipelines, and tool use
- Review evaluation results in a browser-based viewer
- Integrate evaluations and code scans into CI/CD workflows
- Scan code for AI-related security issues
Use cases
- Compare prompt variants across model providers
- Check whether a RAG system answers accurately against test cases
- Scan an AI agent for prompt injection and unsafe tool use
- Run evaluation checks automatically in a CI/CD pipeline
- Review model outputs and failures in the web viewer
Pricing
Community
Free Forever
- All LLM evaluation features
- Red teaming (10k probes/month)
- Run locally or self-host
Enterprise
Custom
- Team sharing and collaboration
- Continuous monitoring
- SSO and granular permission profiles
- Promptfoo API access
On-Premise
Custom
- All Enterprise features
- Deployment on your own infrastructure
- Complete data isolation
- Dedicated runner
Capabilities
- Runs commands — “Run evaluation : Use the command-line tool or library to execute the evaluation and record model outputs for each prompt.” source
- Reviews pull requests — “Get remediation guidance directly in pull requests and developer workflows.” source
- Command line — “promptfoo is an open-source CLI and library for evaluating and red-teaming LLM apps.” source
- Choice of models — “Use OpenAI, Anthropic, Azure, Google, HuggingFace, open-source models like Llama, or integrate custom API providers for any LLM API” source
- Self-hosted — “Run locally or self-host on your own infrastructure” source
- API — “Promptfoo API access” source
- Traces and evaluates — “Test and evaluate your prompts, models, and RAG pipelines” source
Latest updates
- Open-Sourcing ModelAudit: Security Scanner for ML Model Files
ModelAudit was released as an MIT-licensed open-source static scanner for ML model files.
- Building a Security Scanner for LLM Apps
Promptfoo is adding code scanning for LLM-related vulnerabilities, first as a GitHub Action that reviews pull requests.
- GPT-5.2 Initial Trust and Safety Assessment
Promptfoo opened a PR for GPT-5.2 support.
- Real-Time Fact Checking for LLM Outputs
Promptfoo added a search-rubric assertion that uses a separate judge to verify answers against current information.
Where it works
Web · CLI · VS Code · API
Security
Alternatives to Promptfoo
- DeepEval
Open-source framework for testing and evaluating LLM applications locally and in CI.
- Braintrust
Braintrust helps teams inspect AI-agent activity, evaluate outputs, and find production issues.
- Langfuse
Langfuse traces AI applications, manages prompts, and evaluates model and agent outputs using cloud or self-hosted deployments.
- DeepSource
DeepSource reviews code and scans repositories for bugs, security issues, dependency risks, and code-quality problems.
- Arize Phoenix
Arize Phoenix helps developers trace, evaluate, debug, and improve AI applications and agents.
- PromptLayer
PromptLayer helps AI teams manage and test prompts, evaluate outputs, and monitor production requests and agent workflows.
Questions about Promptfoo
Is Promptfoo free?
Yes. The maker’s pages state that Promptfoo can be used for free. Read on the maker’s pages on 18 Nov 2026.
How much does Promptfoo cost?
The maker’s pricing page prints no amount: prices are on request. Prices checked on 6 Nov 2026.
Does Promptfoo have an API?
Yes. The maker’s pages state that Promptfoo has an API. Read on the maker’s pages on 18 Nov 2026.
Which platforms does Promptfoo run on?
Promptfoo runs on Web, CLI, VS Code and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.
Is Promptfoo open source?
Yes. The code of Promptfoo is published at github.com/anthropics/courses. Read on the maker’s pages on 18 Nov 2026.
Is Promptfoo still available?
Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that Promptfoo has ended.
What changed recently in Promptfoo?
The latest entry in its maker’s changelog: 3 Mar 2026, “Open-Sourcing ModelAudit: Security Scanner for ML Model Files”. Before it: 16 Dec 2025, “Building a Security Scanner for LLM Apps”. Changelog checked on 14 Nov 2026.
Sources
- https://www.promptfoo.dev/pricing/ — Official plan names, printed prices, plan features, and Community probe limit.
- https://www.promptfoo.dev/ — Product overview, red teaming, integrations, evaluations, and code scanning.
- https://www.promptfoo.dev/docs/getting-started/ — Evaluation setup, test cases, providers, assertions, CLI, and browser-based viewer.
- https://github.com/promptfoo/promptfoo — Repository confirms the project is open source and MIT licensed.
- https://github.com/promptfoo/promptfoo/releases — Latest displayed release, version 0.126.0, dated 2026-11-18.
Not confirmed
- Prices
- The cheapest paid plans are labeled Custom, with no specific amount shown.