Runtime, the conference for engineers running AI in production. Oct. 1 in SF Register now

Inkling NVFP4

Inkling is Thinking Machines Lab's open-weights multimodal model: a 975-billion-parameter Mixture-of-Experts model that reasons over text, images, and audio with a context window of up to one million tokens.

Model

Inkling uses a sparse, 66-layer decoder-only Mixture-of-Experts architecture with 41B parameters active per token. It is designed for reasoning, coding, tool use, and general multimodal work. Full details are in Thinking Machines Lab's announcement.

Shared Endpoint

On a Shared Endpoint, you pay per token. The endpoint is OpenAI-compatible and already live: point your existing SDK at it and start sending requests.

Dedicated Endpoint

Docs

A Dedicated Endpoint is your own deployment of Inkling NVFP4, on an inference stack that Modal tunes and autoscales. Bring fine-tuned weights if you have them. Compute is billed by the second, and only while it runs.

$ modal endpoint create --model thinkingmachines/Inkling-NVFP4

Related resources

Ship your first app in minutes.

Get Started

$30 / month free compute