Orq.ai
orq.ai
- Free plan
- Web
- API
- Self-hosted
What Orq.ai is
Orq.ai is an AI gateway for routing, governing, and observing requests to models and tools. Through an OpenAI-compatible API, it lists access to 500+ models from 30+ providers. Smart Router can select models using cost or quality strategies, with fallbacks, retries, and load balancing. Governance controls include budgets, spend limits, guardrails, PII redaction, and virtual API keys. Observability covers request traces, cost and token tracking, dashboards, usage analytics, and OpenTelemetry ingestion. Integrations include OpenAI and Anthropic APIs, Python and Node SDKs, remote MCP servers, Azure AI Foundry, Vertex AI, and compatible model endpoints. It supports Claude Code, Cursor, Codex, and 25+ agent frameworks. Deployment options are EU SaaS, VPC, on-premises, and self-hosted. Orq.ai states prompts, outputs, and traces are not used for model training, and lists EU residency and retention controls.
Who it suits
The platform is aimed at engineering and product teams building and shipping LLM applications together. It also suits organizations needing provider routing, spending controls, and deployment choices.
Good to know, and what to watch
- Access to 500+ models from 30+ providers
- Fallback routing, retries, and load balancing
- Budgets, spend limits, and PII redaction
- Request traces and cost tracking
- EU SaaS, VPC, and on-premises options
- Pay-as-you-go includes usage thresholds
- Extra spans and data incur separate charges
- Enterprise pricing is custom
- Model traffic is billed at provider rates
Plans
Every plan and priceEnterprise
Pay-as-you-go
The verdict
Orq.ai combines model access, routing policies, governance, and observability in one gateway. Its free pay-as-you-go entry has defined usage limits, while larger deployments require custom terms.
What the maker publishes
- Agent frameworks
- The gateway lists support for Claude Code, Cursor, Codex, and 25+ agent frameworks. source
- Data handling
- Orq.ai states that prompts, outputs, and traces are never used to train models, and lists EU data residency and retention controls. source
- Deployment
- Listed deployment options include EU SaaS, VPC, and on-premises. source
- Founded
- 2023 source
- Governance
- Gateway controls include budgets, spend limits, guardrail rules, and PII redaction. source
- Headquarters
- Amsterdam, Netherlands source
- Integrations
- The pricing page lists compatibility with OpenAI and Anthropic APIs, Python and Node SDKs, remote MCP servers, Azure AI Foundry, Vertex AI, and OpenAI-compatible model endpoints. source
- Intended users
- The company describes Orq.ai as a platform for engineering and product teams building and shipping LLM applications together. source
- Models and providers
- The platform lists access to 500+ models from 30+ providers through an OpenAI-compatible API. source
- Notable usage limits
- Pay-as-you-go includes 100,000 spans and 1 GB of processed data per month, with extra usage priced separately. source
- Observability
- Orq.ai provides request traces, cost and token tracking, dashboards, and OpenTelemetry ingestion. source
- Routing
- Smart Router can choose a model by cost and quality strategy, with fallbacks, retries, and load balancing available. source
- Security and compliance
- The pricing page states that the platform is SOC 2 Type II and ISO 27001 certified on every plan. source
- Support
- The pricing page lists email support with priority SLA and a Slack or Teams channel as a Teams add-on; Enterprise includes Slack/Teams support. source
- What it does
- Orq.ai provides an AI gateway and platform to route, govern, and observe AI model and tool requests. source
Checked against the maker's pages on 8 Oct 2026.