Skip to main content

OctomilDocumentation API Reference API Explorer Research

Pricing Dashboard

responses

responses

📄️ Run inference and stream tokens as they are produced.

Run inference and stream tokens as they are produced.

Get model recommendations for a device group and capability. Returns ranked catalog variants with coverage, quantization

Run inference and stream tokens as they are produced.

Product

How it works
Compare vs Flower
Pricing
Dashboard

Resources

Quickstart
API reference
Python SDK
Blog

Company

About
Trust center
Security
Contact

© 2026 Octomil