Thinking Machines models
Which Thinking Machines models can you run on Modal?
Thinking Machines
Inkling 2 Small
Thinking Machines Lab's multimodal model for agentic coding, visual reasoning, and knowledge work, with adjustable reasoning effort and a 1M-token context window.
Text VisionThinking Machines
Inkling NVFP4
An open-weights multimodal model with controllable reasoning across text, images, and audio.
Multimodal Vision
| Model | Architecture | Context | Modalities | Input / Output |
|---|---|---|---|---|
| Inkling 2 Small | 594B MoE | 1M | Text · Image | $0.30 / $1.00 |
| Inkling NVFP4 | 975B MoE | 1M | Text · Image · Audio | $1.20 / $5.00 |
All prices per million tokens. Dedicated Endpoint compute is billed by the second. See compute pricing.
Latest updates

Scaling Intelligence: A landmark commission and exhibition
Company

Sandbox resourcing: burst, don't reserve
Why you're paying for capacity you aren't using, and how to pay only for what you use.
Product

Modal becomes a gVisor maintainer
Modal runs upwards of 40 million gVisor containers every day. Here's why we bet on it, what we've built into it, and where we want to take it next.
Company
