View on models.dev 
View on OpenRouter Thinking Machines Lab
Introducing Inkling-Small
An open-weights model that matches Inkling at a quarter of the size: multimodal, Mixture-of-Experts, with controllable reasoning effort. Fine-tune it on Tinker.
Thinking Machines Lab
Inkling
Thinking Machines Lab's first open-weights model: a multimodal Mixture-of-Experts reasoner (975B total, 41B active) with controllable reasoning effort, fine-tunable on Tinker.
Specs
Model
- Family
- Inkling
- Weights
- Open
Limits
- Context
- 65,536 tokens
- Max output
- 65,536 tokens
Modalities
- Input
- Text Image
- Output
- Text
Pricing
- Input
- $1.87 / 1M
- Output
- $4.68 / 1M
- Cache read
- $0.374 / 1M
Capabilities
- Reasoning
- Yes
- Reasoning control
- On / off, Effort levels
- Tool calling
- Yes
- Attachments
- Yes
Dates
- Released
- 15 Jul 2026
