T
Thinkingmachines: Thinking Machines: Inkling Small
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.
Specifications
| Attribute | Value |
|---|---|
| Lab | Thinkingmachines |
| Tags | Intelligent Coding Reasoning Agentic Open Weight Multimodal Image Input Long Context |
| Release Date | 2026-07 |
| Context Window | 524,288 tokens |
| Input Price / 1M | $0.50 |
| Output Price / 1M | $1.20 |
| Input Modalities | Text, Image, Audio |
| Output Modalities | Text |
Strengths
- Supports text and image input with text output
- 512K-token context window for long documents
- Low input pricing for cost-sensitive production workloads
- Tool-use support for agentic workflows
Weaknesses
- Newer listing with limited independent benchmark coverage
- Multimodal performance may vary by provider endpoint
Best For
- Agentic workflows and tool-using applications
- Multimodal document and screenshot analysis
- Long-context document and codebase processing
In Depth: Thinking Machines: Inkling Small
Summary
Thinking Machines: Inkling Small is an AI model from Thinkingmachines.
Released 2026-07. It supports Text, Image, Audio input and produces Text output, with a context window of 524,288 tokens. Input pricing is $0.50 per 1M tokens and output is $1.20 per 1M tokens on OpenRouter.