Orq.ai
Amsterdam AI gateway that records every routed request as a trace, with evaluation, governance and EEA processing
Quick Overview
| Company | Orq.AI Holding B.V. |
|---|---|
| Category | LLM Observability and Evaluation Tools |
| Headquarters | Amsterdam, Netherlands |
| Founded | Not stated |
| EU Presence | Yes - Netherlands (EU) |
| Data Location | Processed in the EEA per its privacy notice |
| Open Source | No |
| GDPR Compliant | Yes |
| Self-Hosting | Enterprise - on-prem and VPC deployment options |
| Main Features | AI gateway, 500+ models, traces with cost and latency, OpenTelemetry, evaluation, guardrails, PII redaction, budgets, audit logs, MCP gateway |
| Pricing | Pay-as-you-go: 4.5% fee on Orq-managed keys; 1M free BYOK requests a month, then 4%; Enterprise on request |
| Best For | Teams that want one governed endpoint for all models with traces included |
| Replaces | Helicone, LangSmith, Portkey-style gateways |
Detailed Review
Orq.ai now leads with an AI gateway and a Software Factory product, and observability is part of the same control plane. Every request routed through the OpenAI-compatible endpoint becomes a trace with cost, tokens, latency and full payloads, with native OpenTelemetry support.
The platform is provided by Orq.AI Holding B.V., registered with the Dutch chamber of commerce, with an Amsterdam address. The privacy notice says information is processed in the EEA, and the service terms are governed by Dutch law.
Observability through the gateway
Because traffic goes through the gateway, nothing extra has to be instrumented to get traces. The pricing page counts each routed request, agent step, evaluator or guardrail run as one span, with 100k spans a month before a charge of EUR 7 per 100k.
Controls on the same path
Budgets, spend limits, guardrail rules and PII detection and redaction are applied to each request, and the vendor says they can alert or hard-block before spend happens. Enterprise adds AI governance, audit logs and a custom DPA.
Pricing
Pay-as-you-go has unlimited gateway seats, a 4.5% fee when using Orq-managed model keys, and 1M free requests a month with your own keys, then 4%. Enterprise adds on-prem and VPC options, a SOC 2 report and ISO 27001, priced on request.
Limitations to Consider
Orq.ai is gateway-first: the site now emphasises routing and a software-delivery product, and its traces cover requests that pass through it. It is not open source, and self-hosting is an Enterprise option. Teams that only want a tracing library and an evaluation workspace may find Latitude or LangWatch more focused. The privacy page does not name a cloud region.
Who Should Use Orq.ai
Teams that want to route all model traffic through one European-operated gateway and get traces, budgets and guardrails without extra instrumentation.
Pros and Cons
Pros
- Traces for every routed request
- Native OpenTelemetry support
- Budgets, guardrails and PII redaction on the same path
- Processed in the EEA per privacy notice
- Unlimited gateway seats
Cons
- Gateway-first product
- Not open source
- Span and fee metering to estimate
- Self-hosting only on Enterprise
Alternatives to Orq.ai
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 Helicone on our alternatives page.
Frequently Asked Questions
For requests that pass through its gateway, yes: each one becomes a trace with cost, tokens, latency and payloads. Calls that bypass the gateway are not covered.
Its privacy notice says information is processed in the EEA and that the company has its headquarters in the Netherlands.
Pay-as-you-go charges 4.5% when you use Orq-managed keys, or 1M free requests a month with your own keys and 4% afterwards. Enterprise is priced on request.