Qualifire
Israeli guardrails and evaluation platform built on small judge models, deployable in your cloud or on-premise
Quick Overview
| Company | Qualifire Ltd. |
|---|---|
| Category | LLM Observability and Evaluation Tools |
| Headquarters | Israel (city not stated), Israel |
| Founded | Not stated |
| EU Presence | Yes - Israel (counts as European for EP) |
| Data Location | SaaS, your cloud or on-premise; facilities in Israel per privacy policy |
| Open Source | No |
| GDPR Compliant | Yes |
| Self-Hosting | Enterprise - BYOC cloud or on-premise |
| Main Features | Contextual guardrails, evaluations, observability, prompt studio, small language model judges, PII masking, hallucination and grounding checks, Rogue agent evaluator |
| Pricing | Free plan; Pro $550/month; Enterprise on request |
| Best For | Teams that want real-time policy enforcement and evaluation, not only after-the-fact tracing |
| Replaces | LangSmith, Arize, guardrail add-ons |
Detailed Review
Qualifire joins runtime guardrails and evaluation. Small judge models check prompt injection, PII, hallucination, grounding and custom policies on each request, and the same results feed an observability view and a prompt studio with experiments.
The terms are issued by Qualifire Ltd. and are governed by the laws of the State of Israel. The privacy policy says the company has facilities in Israel and relies on the European Commission adequacy decision for Israel.
Guardrails and judges
The product page describes judge models tailored to a business domain and policies, aimed at low latency and low cost. Rogue, an open evaluator and red-team tool, is linked from the homepage.
Deployment
Plans list SaaS, hosted on your cloud, or on-premise. Enterprise adds BYOC cloud or on-prem deployment, SAML SSO, 24/7 support and seven-year log retention.
Pricing
The pricing page lists a free plan, a Basic plan at $0 with 300k monthly tokens and a Pro plan at $550 per month with 1 billion monthly tokens, unlimited protection rules and 90-day log retention.
Limitations to Consider
The pricing page is not consistent: the free plan says 3 million tokens a month while the Basic card says 300k, so confirm limits before relying on them. Log retention is 7 days on the basic tier. The jump to Pro is $550 a month. It is guardrail-first, so a team that mainly wants a trace explorer for debugging would be better served by LangWatch. Prices are in dollars.
Who Should Use Qualifire
Teams that need runtime policy enforcement and evaluation together, with the option to keep the system in their own cloud.
Pros and Cons
Pros
- Guardrails and evaluation in one tool
- Small judge models for low latency
- BYOC and on-premise options
- Free plan available
- Israeli contracting party under Israeli law
Cons
- Inconsistent free and Basic limits on pricing page
- Seven-day log retention on the basic tier
- $550 per month Pro step
- Prices in US dollars
Alternatives to Qualifire
Other European llm observability and evaluation tools worth comparing before you decide:
LangWatch
Netherlands · Open-source agent tracing, evaluations and simulations from Amsterdam
Latitude
Spain · Open-source agent observability that groups failures into issues
Galtea
Spain · Test generation, simulation and evaluation for regulated industries
Giskard
France · Red teaming and evaluation for LLM agents before release
See all European llm observability and evaluation tools or compare them directly against LangSmith on our alternatives page.
Frequently Asked Questions
No. Its pages list contextual guardrails, evaluations, observability, prompt studio and data curation, but the guardrails are the lead feature.
Yes. The Enterprise plan lists hosting in your cloud or on-premise, and the homepage shows the same deployment options.
Rogue is an evaluator and red-team tool for AI agents that the homepage links to GitHub; the licence was not verified.