MODEL PROFILE

Inkling Small (free)

thinkingmachines · inkling-small:free

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...

Text generationreasoningtools
Context window1,048,576 Token
Input → OutputText、Image、Audio → Text
Model weightsOpen weights
Profile updated2026/11/7 22:09:27
OVERVIEW

Model overview

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 summary below is compiled from sources by an AI model, not our own testing. Verify selection decisions against original sources and your workload.

Key features

  • Multimodal input support for text, image, and audio
  • Mixture-of-experts architecture with 12B active parameters (out of 276B total)
  • Open-weight model designed for efficiency and reasoning-intensive tasks

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
OpenRouter · thinkingmachines/inkling-small:free ↗USD 0USD 0Per million tokens2026/11/2 06:25:22

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

Is Inkling Small truly open-weight?

Yes — the model is described as 'open-weight' in the provided source.

What does '12B active parameters out of 276B total' mean?

It indicates a sparse MoE architecture where only 12 billion parameters are activated per inference, selected from a total pool of 276 billion parameters.

Does Inkling Small support multimodal output?

No — the documented outputs are text-only; no multimodal output (e.g., image or audio generation) is mentioned.

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:来源未披露,须进一步核验。模型介绍与第三方评测均以原来源的具体版本和方法为准。