Skip to main content

Inkling (batch)

General purposeVisionTools

Thinkingmachines · Released July 2026

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Facts and pricing

Provider
Thinkingmachines
Context window
524K tokens
Input price
11.0 credits / 1M tokens ($1.00 raw)
Output price
44.6 credits / 1M tokens ($4.05 raw)
Vision (image input)
Yes
Tool calling
Yes
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Inkling (batch) now

Ask Inkling (batch) anything. Your prompt opens in the Zeplik app with this model selected.

Inkling (batch)

What Inkling (batch) is best for

Thinkingmachines family

ModelContextInput cr/MOutput cr/MReleased
Inkling Small524K5.013.2July 2026
Inkling (batch)524K11.044.6July 2026
Inkling1.0M10.544.6July 2026

Frequently asked questions

What is Inkling (batch)?
Inkling (batch) is an AI model by Thinkingmachines. Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
How much does Inkling (batch) cost on Zeplik?
Input tokens cost 11.0 credits per million and output tokens 44.6 credits per million (1 credit = $0.10; the raw provider rates are $1.00 and $4.05 per million). New accounts start with free credits.
How long can a conversation with Inkling (batch) be?
Inkling (batch) has a 524K-token context window (524,288 tokens), which covers the conversation plus any documents you attach.
Does Inkling (batch) support images and tools?
Inkling (batch) accepts image input and supports tool calling.

Related models

Inkling SmallFast and light

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...

524K ctx13.2 cr/M outJuly 2026
InklingGeneral purpose

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

1.0M ctx44.6 cr/M outJuly 2026
Gemini 3.7 FlashFast and light

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

1.0M ctx20.6 cr/M outAugust 2026
Gemini 3.7 Flash (batch)Fast and light

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

1.0M ctx10.3 cr/M outAugust 2026
Seed 2.1 TurboFast and light

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...

262K ctx27.5 cr/M outAugust 2026
Qwen3.8 2.4T A95BFrontier

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

1.0M ctx66.0 cr/M outAugust 2026

More you can do with Inkling (batch)

Inkling (batch) - Thinkingmachines AI Model | Zeplik Chat