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.
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.
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.
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