- Capture and observe production traffic. Use models from any provider.
- Create and run evals against production data to understand your application.
- Create datasets from observed traffic to train better, task-specific models.
- Deploy models behind a stable production endpoint to use in your application.
Quickstart
Capture & Observe Traffic
Route an existing OpenAI-compatible app through Inference.net and verify your first observed request.
API Quickstart
Make your first direct API call when you want to start from the hosted API instead of Observe.
Search models
Browse the model catalog before you pick an API or deployment path.
Meet with Us
Talk to our team if you want help designing your eval, training, or deployment workflow.
Where to start
| If this sounds like you… | Start here | What comes next |
|---|---|---|
| ”We already use OpenAI or Anthropic and want visibility first.” | /start-here/observe-quickstart | Then create datasets from observed traffic |
| ”We want to prototype directly against the API first.” | /quickstart | Then choose realtime, background, or batch |
| ”We need a release gate before changing models.” | /guides/build-a-real-traffic-eval-baseline | Then use the same eval to decide whether to train or deploy |