OdinLabsTalk to Odin
Menu

One connection. More control over AI.

Connect your tools to AI models through one managed API. Make routing, usage and budgets part of the way your team works.

Talk about AI Gateway All products

AI Gateway

Interactive illustration · fictional data
AI GatewayIllustrative product preview

Route with a reason.

Policy configured
Your toolsOne API connection
Odin AI GatewayRouting · policy · budgets
Quality profileAvailable route
Balanced profileSelected by policy
Cost profileAvailable route

The actual model and usage remain attributable.

Provider choices

Access follows your configuration.

  • Orq
  • EUrouter
  • Requesty
  • OpenRouter

Choose a routing priority

Match capability and cost to everyday work.

One request, accounted for

Fictional request · Summarize a supplier brief

Attribution
Operations · supplier-demo key
Priority
Balanced
Configured route
EUrouter · Mistral
Served model
Mistral Medium 3.1 · example
Static example receipt
Look under the hood

Connect existing tools through an OpenAI-compatible API. The selected profile expresses a routing priority; configured capability, budget and residency policies constrain the route.

Provider choices are separate from routing profiles. This fictional request has one eligible route, so changing its priority keeps the same example model. Actual routes and models depend on configured access and policy. The receipt is not live usage or a claim about processing location.

What it does today

Successful completions report the router-selected model.

Successful responses report the model the router selected, after any fallback, with its configured provider and region, not only the model that was asked for. The latest known spend and remaining budget come back as headers too.

  • X-Odin-Request-Id
  • X-Odin-Served-Model
  • X-Odin-Served-Provider
  • X-Odin-Served-Region
  • X-Odin-Spent-USD
  • X-Odin-Budget-Remaining-USD
OpenAI-compatible
Chat completions with streaming and tool calls, a model list and a usage endpoint. Existing clients change a base URL and a key.
Routing profiles as model names
Ask for odin/auto-quality, odin/auto-balanced or odin/auto-cost; odin/auto-eu keeps a request to EU-jurisdiction routes. A specific catalogued model name pins that model.
Policy per key that only narrows
Each key can be limited by price tier, request rate and residency (EU-only, EU jurisdiction or any). Residency applies to pinned models too and fails closed.
Budgets that stop
At the limit a request is refused with budget_exceeded. If the budget service cannot be reached, requests fail closed. A configured soft threshold records an advisory audit event.

Drawn from the current product source, not the illustration above. What is enabled depends on your configured environment.

Choose a routing profile. Keep the policy in view.

A team uses several AI tools and needs a shared way to manage model access and understand usage.

A familiar connection

An OpenAI-compatible API connects existing applications and developer tools.

Routing with intent

Balance quality, cost and configured residency requirements through routing profiles.

Usage you can account for

Attribute usage to keys, people and models, with budget controls and visibility in Command Center.

Make it work
in your environment.

Provider access, routing policies and budgets are configured for your environment. Talk to us about the tools you want to connect.

Explore implementation services

Start with a real workflow.

Talk to Odin