Trusted by teams where AI spend is mission-critical
Connect in minutes
One API key. Full LLM visibility.
Connect OpenRouter with a read-only API key. DoiT ingests your generation, token, and cost data automatically across every model and provider you route to. No proxies, no code changes, no rewriting your inference calls. You're looking at unified LLM cost reports within hours of connecting.
What you get
Built for the realities of shipping on LLMs
The things FinOps and AI engineering leaders actually ask us for when they connect their OpenRouter account.
Unified LLM cost reporting
Slice OpenRouter spend by model, provider, API key, or team without exporting usage data by hand.
Real-time anomalies
Get alerted on token usage spikes in minutes, not hours.
Model cost comparison
Compare cost per request across models to find cheaper routes for the same workload.
Token-level breakdowns
Split prompt and completion tokens across every provider you route to.
Routing and fallback visibility
See which provider actually served each request, and what fallbacks and retries are quietly costing you.
Governance and budgets
Set budgets per team or API key before a runaway agent burns through credits.
OpenRouter's analytics tell you what happened. Cloud Intelligence™ helps you do something about it.
Beyond the OpenRouter activity page
Per-model cost rollups
Consolidated views across every model and provider you route to, with drilldown into any API key.
Real-time anomaly alerts
Machine-learning detection on model, provider, and key dimensions, routed to Slack or email.
Spend forecasting
Project LLM costs from actual token usage trends before a new feature ships to production.
Key and team allocation
Map API keys to teams and products, and split shared LLM costs the way finance expects.
AI spend alongside cloud spend
See OpenRouter costs next to your cloud bills in one view, so AI is part of the whole picture.
Forward Deployed Engineers
World-class cloud architects who work as an extension of your team to implement optimizations.
Attribute + OpenRouter
Map OpenRouter spend to the work that drives it
Attribute's runtime sensor covers infrastructure and AI inference, mapping OpenRouter costs to customers and workloads without relying on a tagging program. Best for: SaaS teams that want infrastructure and AI cost attribution in one view.
Runtime coverage
Attribute OpenRouter calls made from Kubernetes, VMs, and serverless workloads.
Provider attribution
Cover OpenAI, Anthropic, Google, Meta, and the other providers behind your key.
Self-managed services
Attribute inference calls made from services you run and operate yourself.
Full OpenRouter API coverage
Capture chat completions, completions, and streaming response calls.
Per-model costs
Break down spend across Claude, GPT, Gemini, Llama, and other models.
Customer and workload views
Show which customer and workload is responsible for each cost.
Infrastructure and AI anomalies
Detect unusual spend across cloud services and model inference.
Fast-growing companies run on Cloud Intelligence™
Avg. savings within first 90 days
Avg implementation time
“DoiT's focus on reliability, mixed with the system's flexibility, helps us safely optimize our Amazon EKS workloads with zero-touch from our engineers.”
Oren Ashkenazy
Director of DevOps and Cloud at Fiverr
Ready to connect your OpenRouter account?
Bring your LLM spend into focus.
Frequently asked
questions
How do I get better visibility into OpenRouter costs across models and providers?
Connect your OpenRouter account once. Cloud Intelligence™ ingests generation and cost data for every model and provider you route to, so you can slice spend by model, provider, API key, or team from a single view. No CSV exports, no manual rollups.
How do I connect OpenRouter to Cloud Intelligence™?
Use a read-only OpenRouter API key. DoiT handles the rest: ingestion, normalization, and per-request cost reporting. There are no proxies to deploy and no changes to your inference code. Most teams are live within a day.
How can I see which models or API keys drive most of my LLM spend?
Reports let you drill from total OpenRouter spend down to a specific model, provider, or API key, with prompt and completion tokens broken out. You can filter by team or product without writing any queries.
How can I monitor OpenRouter cost anomalies in real time?
Anomaly detection runs continuously across model, provider, and key dimensions. When token usage spikes, from a runaway agent loop or an unexpected fallback to a pricier model, you get a Slack or email alert with the likely cause before the credits are gone.
How is Cloud Intelligence™ different from OpenRouter's built-in activity and analytics pages?
OpenRouter's dashboard is a usage log for one account. Cloud Intelligence™ is a platform: team-level allocation, budgets, real-time anomaly detection, spend forecasting, LLM costs alongside your cloud bills, and access to forward deployed engineers who help you act on what the data shows.
I use BYOK with my own provider keys. Does that usage still show up?
Yes. Requests routed through OpenRouter are captured regardless of whose key served them, so you keep one consistent view of model usage and cost even when spend lands on your own provider accounts.
Can I see OpenRouter spend next to my cloud spend?
Yes. Cloud Intelligence™ is multi-cloud by design, so OpenRouter costs sit alongside your cloud provider bills. You can build reports and budgets that treat AI inference as part of your total cost of goods, not a separate silo.
Is my data secure when I connect my OpenRouter account?
Cloud Intelligence™ uses a read-only API key with least-privilege access. We never see prompt or completion content, only usage and cost metadata, we never make changes without your approval, and the platform is SOC 2 Type II certified.