IQ Routing
Route each LLM call to the cheapest model that still maintains quality, reducing large-model call costs.
About IQ Routing
IQ Routing is a routing gateway that sits in front of chatbots, RAG pipelines, agent loops, and financial workloads. It routes each call to the cheapest model that still maintains quality, which the company says can cut spending by 40% to 80% on its own traffic, and can be deployed in under thirty seconds. It works as a drop-in replacement for the OpenAI and Anthropic base URLs, covering OpenAI, Anthropic, and Google with a single URL, and supports bring-your-own-key (BYOK).
Best for
Best use cases
Routing each step in an agent loop (planning, retrieval, tool calls, synthesis, verification) to the cheapest model that still maintains quality
Unifying access to OpenAI, Anthropic, and Google through a single URL
Avoiding duplicate billing for repeated calls through semantic caching
Capping spending before runaway loops overspend using a cost envelope
Features
Smart routing
Routes each call to the cheapest model that still maintains quality, which the company says can cut spending by 40% to 80% on its own traffic.
Drop-in integration
Works as a drop-in replacement for the OpenAI and Anthropic base URLs, covering OpenAI, Anthropic, and Google with a single URL.
Bring your own key
Every plan supports bring-your-own-key (BYOK): connect your own provider keys and pay providers directly.
Semantic caching
Repeated calls are served from cache instead of being billed again.
Cost envelope
A cost envelope caps spending before runaway loops overspend.
Zero Data Retention
Zero Data Retention is an organization-level setting available on every plan (including Free); when enabled, payload logging and telemetry retention are disabled and locked.
Gateway PII redaction
An organization-level setting that detects and redacts common identifiers (such as email addresses, phone numbers, Social Security numbers, and card numbers) before request payloads reach upstream providers; off by default.
Pros
- Works as a drop-in replacement for the OpenAI and Anthropic base URLs
- Covers OpenAI, Anthropic, and Google with a single URL
- Supports bring-your-own-key (BYOK), paying providers directly
- Offers semantic caching, audit trails, capability resolver, and cost envelopes
- Provides Zero Data Retention settings and gateway PII redaction
Pricing Plans
Team
- Billed monthly, no annual plan
- Everything in Free plus alerting, org-scoped access, and custom band maps.
- Usage limit 600 requests/min
Enterprise
- Custom annual contract
- On-prem deployment, SOC2 evidence pack on request, dedicated support.
- Usage limit 6,000+ requests/min
- Everything in Free
- Per-team budgets
- Audit log
- Per-team alerting
- Org-scoped access controls
- Custom band maps (auto, cheap, frontier)
- Priority email support
* Pricing information is for reference only. Please refer to the latest announcement on IQ Routing's official website.