AI Rate Card

Inkling Small · deepinfra

Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable thinking effort

Base modelAll models on this baseAll models of the providerto the provider

Input, $/1M $0.45

Output, $/1M $1.20

Limits

  • Every plan: 200 requests at once

Last checked 04.11.2026 12:08:11 UTC Source

Context 524 288

Accepts audio, images, text

Last checked 04.11.2026 12:00:14 UTC

Source —

Price alerts

Sign in to follow the price

API

This model type has no common request format: see the provider's documentation.

Provider's API documentation

Source: AI Rate Card, https://airatecard.com/en/c/offer%3Adeepinfra%7Cthinkingmachines/Inkling-Small, prices checked 2026-11-04

Technical details

ID: offer:deepinfra|thinkingmachines/Inkling-Small