T
Inkling 2 Mini
Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE).
Specifications
| Lab | Thinking Machines |
|---|---|
| Context window | 1M tokens |
| Input price | $0.10/1M |
| Output price | $0.40/1M |
| Release | Nov 2026 |
Strengths
- Open-weight MoE (3.4B active / 26.4B total) with looped transformer layers
- 1M-token context window
- Multimodal input (text + image)
- Adjustable reasoning effort (minimal to max)
- Ultra-low API pricing
Weaknesses
- Small active parameter count limits ceiling on hard reasoning tasks
- Early Artificial Analysis intelligence index (20.1) trails larger siblings
- Looped weight-sharing architecture is less proven at scale
Best for
- High-volume agentic workloads
- Cost-sensitive coding assistance
- Long-context retrieval tasks
In Depth: Inkling 2 Mini
Summary
Inkling 2 Mini is an AI model from Thinking Machines.
Released in Nov 2026. It takes text and image input and produces text output, with a context window of 1M tokens. Input pricing is $0.10 per 1M tokens and output is $0.40 per 1M tokens on OpenRouter.