Thinking Machines Lab: the Inkling family of open models
Try open-weight models from Thinking Machines Lab, built for reasoning, agentic coding, and multimodal understanding, served on Crusoe infrastructure.
Start with a model built to be fine-tuned
Thinking Machines Lab designed Inkling to be a starting point, not a finished product, an open model teams adapt to their own data and expertise. On Crusoe, run it on a dedicated endpoint through Self-Serve Deployments, with capacity you control rather than a shared queue.
Pick the precision that fits your budget
Inkling ships in full and quantized builds. Run the quantized version to cut memory use and raise throughput on the same GPU, or the full build when accuracy matters most, each on its own dedicated endpoint through Self-Serve Deployments.
Your data stays on Crusoe Cloud
Inkling runs entirely on Crusoe-operated infrastructure. Your prompts, outputs, and fine-tuning data stay with Crusoe and are never sent to Thinking Machines Lab.
Fine-tune and deploy in Crusoe Intelligence Foundry
Frequently
asked questions
Thinking Machines Lab is a San Francisco-based AI lab founded in 2025 by former OpenAI CTO Mira Murati. It develops the Inkling family of open-weight models, released under the Apache 2.0 license and designed as bases that organizations adapt to their own data and expertise. On Crusoe Cloud, Inkling models are available for high-performance inference via Self-Serve Deployments, running on Crusoe-operated infrastructure with no customer data sent to Thinking Machines Lab.
The best Inkling model is the one that matches your priority: quality, speed, or cost. Larger Inkling models offer the broadest knowledge and the highest quality, while smaller ones deliver strong reasoning and coding performance at a lower serving cost. Quantized versions reduce memory use and raise throughput with a small accuracy tradeoff. Check each model’s details for current capabilities and supported services.
Yes. Inkling’s open weights can run on any infrastructure, so prompts and outputs never need to pass through Thinking Machines Lab’s own platform. Data handling is governed by whoever hosts the model, not by the lab that trained it. On Crusoe Cloud, Inkling models run on Crusoe-operated infrastructure, and no customer data is sent to Thinking Machines Lab.
Start in Crusoe Intelligence Foundry. Deploy Inkling on a dedicated endpoint through Self-Serve Deployments, tuned for throughput or responsiveness, or request a Tailored Deployment for an SLA-backed endpoint. Each model’s details show the services it currently supports.
