Thinking Machines Lab logo

Inkling

Thinking Machines LabOpen WeightsPending Human Review

Inkling is Thinking Machines Lab’s open-weight multimodal mixture-of-experts model, trained from scratch for native reasoning over text, images, and audio. Variable thinking effort allows applications to choose a latency and reasoning tradeoff. The checkpoint supports up to 1M tokens, while hosted product limits can be lower. Apache-licensed weights and Tinker access enable customization and deployment for coding, conversational assistants, and tool-using agents. Its pretraining includes 45T tokens spanning text, images, audio, and video; video training does not establish a supported direct video-input endpoint.

2026-07-15
975B total, 41B active
Mixture-of-Experts Transformer
Apache-2.0

Specifications

Parameters
975B total, 41B active
Architecture
Mixture-of-Experts Transformer
License
Apache-2.0
Context Window
1,048,576 tokens
Type
multimodal
Modalities
textimageaudio

Benchmark Scores

Advanced Specifications

Model Family
Inkling
API Access
Available
Chat Interface
Not Available

Capabilities & Limitations

Capabilities
multimodal reasoningcodingtool useadjustable reasoninglong context
Known Limitations
Full weights require substantial distributed-serving memoryHosted Tinker context limits differ from checkpoint capacityModel-card evaluations are provider-reported
Notable Use Cases
customizable assistantsmultimodal agentsprivate model research
Tool Use Support
Yes

Related Models