Thinkingmachines
Available in Shortly AI
Inkling Small
Released July 30, 2026
ReasoningVision (Image)Tool Use
Inkling-Small is a lighter-weight model with 12B active parameters, trained with a similar recipe, to Inkling that achieves strong performance with even lower cost and latency.
- Context window
- 1M tokens
- Maximum output
- 1M tokens
- Input pricing
- $0.50/M
- Output pricing
- $1.20/M
FAQ
Similar AI models
Gemini 3.5 Flash LiteGoogleGemini 3.5 Flash Lite features upgraded agentic capabilities, making the model ideal for subagents in complex workflows.Gemini 3.6 FlashGoogleGemini 3.6 Flash delivers higher quality across coding, agentic workflows, and web development with reduced token consumption and fewer model calls compared to previous model iterations.InklingThinkingmachinesInkling is a multimodal MoE model (975B total, 41B active, 256k context) reasoning over text, image, and audio inputs.
Available with one subscription
Start with Inkling Small in Shortly AI
Keep your conversations, files and model choices together in one workspace.