WHY WE PICKED IT
It is the first roughly trillion-parameter open-weights model that takes audio and images natively rather than through a bolted-on encoder, and Apache 2.0 means the weights can be used commercially without asking anyone. Thinking Machines is candid that this is not the strongest model available but a base worth customising, which is a more honest pitch than most open releases make.
GETTING STARTED
Pull the weights from huggingface.co/thinkingmachines/Inkling, or skip the hardware and call it through Together AI, Fireworks, Modal, Databricks or Baseten. For local work, the NVFP4 checkpoint is the one to use on Blackwell cards; everyone else should start from the original checkpoint on vLLM or SGLang. If the plan is to fine-tune rather than use it as shipped, that is what Thinking Machines built the Tinker platform for.
QUICK TIPS
1
Feed audio as 16kHz WAV under about 20 minutes, which is the range it was tuned for
2
Keep images between roughly 40px and 4096px on the long edge
3
Use the controllable thinking effort setting rather than paying for maximum reasoning on every call
4
Treat the vendor benchmark numbers as an upper bound, they were run at effort 0.99 and temperature 1.0
5
Try a hosted inference provider before committing to 975B of self-hosted infrastructure
❓
FREQUENTLY ASKED QUESTIONS
Q
Is Inkling free?
A
Yes, Inkling is completely free to use.
Q
Does Inkling have an API?
A
Yes, Inkling offers an API for programmatic integration.
Q
What is Inkling best for?
A
Inkling is best for Best Open-Weight Multimodal Base. Inkling is the first open-weights model from Thinking Machines Lab, released 15 July 2026 under Apache 2. It is the first roughly trillion-parameter open-weights model that takes audio and images natively rather than through a bolted-on encoder, and Apache 2.0 means the weights can be used commercially without asking anyone. Thinking Machines is candid that this is not the strongest model available but a base worth customising, which is a more honest pitch than most open releases make.
Q
What platforms does Inkling support?
A
Inkling supports api, local.
Q
Is Inkling open source?
A
Yes, Inkling is open source. You can access the source code, contribute, and deploy it on your own infrastructure.
Q
How do I get started with Inkling?
A
Pull the weights from huggingface.co/thinkingmachines/Inkling, or skip the hardware and call it through Together AI, Fireworks, Modal, Databricks or Baseten. For local work, the NVFP4 checkpoint is the one to use on Blackwell cards; everyone else should start from the original checkpoint on vLLM or ...
Q
How do I use Inkling?
A
Inkling is a large language model for text generation, analysis, and conversation. Use the API for programmatic access. Enter prompts or questions to get responses. It excels at apache 2.0, the least restrictive licence of any model at this scale.
Work on Inkling? You're hand-reviewed in our directory. Add this badge to your site — it links back to this profile.
