Model
The model or model family requested.
Catalog examples
RouterLab sits between your applications, agents, workflows, and model routes. It authenticates the request, applies the selected route, then attaches the response to usage and credits.
Product schematic
Existing
Application
OpenAI SDK
Existing
AI agent
Claude Messages API
Existing
Workflow
Job / automation
Replace the base URL
from
api.openai.com/v1
to
api.routerlab.ch/v1
ROUTERLAB
Routes · credits · statuses
OpenAI
External provider route
Anthropic
External provider route
External provider route
RouterLab
RouterLab-hosted open-source models · CH / DE
Dashboard usage
Illustrative example
Usage
1,248 req
Credits
CHF 42.80
Response
back to client
After request
usage + credits
Concepts
These three levels answer three different questions: what to use, how to call it, and who executes the request.
The model or model family requested.
Catalog examples
The protocol the client uses to call RouterLab.
Catalog examples
The infrastructure that actually executes the request.
Catalog examples
Before / with RouterLab
The homepage explains why RouterLab exists. This page shows what changes in the technical flow.
Detailed flow
The sequence stays short: keep integration simple, make routing and usage observable.
Your application, agent, or compatible SDK sends the request.
RouterLab authenticates the key and receives the request.
The selected route determines the format and destination.
The request is processed by the provider or infrastructure specified by the route.
The response returns to the client; RouterLab attaches usage and credits.
Endpoint and compatibility
RouterLab exposes compatible formats. The change is the base URL and RouterLab key; the exact path then depends on the SDK you use.
https://api.routerlab.ch/v1
Change the entry point, then read routes and usage instead of guessing what happened.
SDKs can use a slightly different base URL because each one builds its own API path. They still reach the same RouterLab layer.
https://api.routerlab.ch/v1
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.routerlab.ch/v1",
apiKey: process.env.ROUTERLAB_API_KEY,
});
await client.chat.completions.create({
model: "model-id-from-/v1/models",
messages: [{ role: "user", content: "Route this request" }],
});https://api.routerlab.ch
import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({
baseURL: "https://api.routerlab.ch",
apiKey: process.env.ROUTERLAB_API_KEY,
});
await client.messages.create({
model: "model-id-with-claude-messages-route",
max_tokens: 1024,
messages: [{ role: "user", content: "Route this request" }],
});Control
The modules are concrete: keys, credits, usage, and catalog. They operate AI traffic without adding an automatic-routing promise.
Apps keep one stable entry point without exposing every provider key.
Cost is attached to requests and the credit ledger.
The dashboard shows the route, format, and cost associated with the request.
Models, formats, and statuses remain visible when choosing a route.
Governance
The catalog separates model family, API format, and processing path. RouterLab does not present a provider as if it were a model.
The control layer, published routing, and visibility.
Each provider operates its infrastructure and models.
Route table
| Model / family | API format | Processing / hosting | What it means |
|---|---|---|---|
| Claude | Claude Messages API | External provider | Claude is a model family called with the Messages format; infrastructure depends on the catalog route. |
| GPT | OpenAI-compatible API | External provider | GPT is a model family; OpenAI-compatible describes the protocol, not the final infrastructure by itself. |
| Gemini | OpenAI-compatible API | External provider | Gemini is a model family; the call format and processing provider are separate pieces of information. |
| Open-source families | OpenAI-compatible API | RouterLab when hosted; otherwise external provider | Open source describes the model family or type; hosting must be read route by route. |
| Embedding models | Embeddings API | Processing follows the catalog route | Embedding models use a specialized route and are not chat models. |
A route can target an external provider or host an open-source model with RouterLab. Hosting and processing are read route by route; see the Trust page for relevant infrastructure information.
Trial
Start with a trial key, then use the catalog to choose the right routes.