Skip to main content

docs.inertialai.com

Build on real-world data.

Two products, one API key: a chat model that reads your sensor streams, metrics, markets, and health signals — and self-serve finetuning that makes it yours.

Get StartedAPI Reference

quickstart.py

from openai import OpenAI

client = OpenAI(
    base_url="https://inertialai.com/api/v1",
    api_key="iai_...",
)

resp = client.chat.completions.create(
    model="inertialai-0.1",
    messages=[{
        "role": "user",
        "content": "Pump vibration (mm/s): 2.1, 2.0, 2.2, 4.8, 5.1. "
                   "One word: normal or anomaly?",
    }],
    logprobs=True,  # calibrated token-level confidence
)

print(resp.choices[0].message.content)  # "anomaly"

inertialai-0.1

InertialAI-0.1

The chat model for physical data, behind an OpenAI-compatible API. Paste readings, ask questions, and get answers with calibrated token-level confidence you can threshold on. $0.25/1M input, $1.25/1M output.

Chat with your data

chronicle

Chronicle

Self-serve finetuning on your data. Upload, train from $5, get an automatic before/after eval against the frozen base — refunded if it doesn't win — and deploy to a private scale-to-zero endpoint.

Finetune on your data
PlatformAuth, API keys, billing, credits, and GPU serving rates.API ReferenceEvery endpoint and schema, with runnable examples.Other EndpointsEmbeddings, forecasting, the Python SDK, and integrations.