Thinkingmachines

Thinking Machines: Inkling Small (batch)

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...

Context Window
524K tokens
Parameters
12B
Input Price
$0.50/1M
Output Price
$1.20/1M
Price Tier
standard
Provider
Thinkingmachines

How to Use Thinking Machines: Inkling Small (batch)

With CoreAI, you can start chatting with Thinking Machines: Inkling Small (batch) instantly — no separate subscription needed. CoreAI lets you chat with Thinking Machines: Inkling Small (batch) alongside 300+ other AI models from Thinkingmachines and other providers like OpenAI, Anthropic, Google, Meta, and more.

  1. Download the CoreAI app for iOS, Android, or use the Web App
  2. Select Thinking Machines: Inkling Small (batch) from the model selector
  3. Start chatting, comparing, or creating with AI

Thinking Machines: Inkling Small (batch) at a Glance

Measured against all 378 chat models CoreAI serves, Thinking Machines: Inkling Small (batch) sits at #119 for context capacity — 524K tokens, roughly 393,216 words or 786 pages of text in a single conversation. On price, it is the #66 cheapest of 181 standard-tier models by input cost. It joined the catalog on 2026-07-30. It supports step-by-step reasoning (thinking mode) and accepts image input.

Thinking Machines: Inkling Small (batch) Compared to Its Closest Alternatives

SpecThinking Machines: Inkling Small (batch)Thinking Machines: Inkling SmallMiniMax: MiniMax M3Mistral: Mistral Nemo
ProviderThinkingmachinesThinkingmachinesMinimaxMistral AI
Input $/1M tokens$0.5$0.45$0.3$0.019
Output $/1M tokens$1.2$1.2$1.2$0.03
Context window524K524K524K131K
Reasoning modeYesYesYesNo
Image inputYesYesYesNo
Price tierstandardstandardstandardbudget

Every model in this table is available on CoreAI — open the web app and run the same prompt through Thinking Machines: Inkling Small (batch) and Thinking Machines: Inkling Small side by side to judge with your own eyes.

What Thinking Machines: Inkling Small (batch) Actually Costs in Practice

A typical question (about 1,000 tokens in, 500 out) runs $0.00110 on Thinking Machines: Inkling Small (batch)'s raw per-token rates; a heavy session with a 50K-token document costs about $0.031. On CoreAI you don't juggle these numbers — one subscription covers Thinking Machines: Inkling Small (batch) and 300+ other models under a plan usage limit, with no API keys. See plans.

More Thinkingmachines Models

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 po
524K standard
Thinkingmachines

Thinking Machines: 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 po
1049K budget
Thinkingmachines

Thinking Machines: Inkling

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
524K standard
Thinkingmachines

Thinking Machines: Inkling (batch)

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
524K standard
Thinkingmachines

Thinking Machines: Inkling (free)

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
1049K budget

Frequently Asked Questions about Thinking Machines: Inkling Small (batch)

What is Thinking Machines: Inkling Small (batch)'s context window?

Thinking Machines: Inkling Small (batch) handles 524K tokens of context — roughly 393,216 words, or about 786 pages of text in one conversation.

How much does Thinking Machines: Inkling Small (batch) cost?

Thinking Machines: Inkling Small (batch)'s underlying rates are $0.5 per 1M input tokens and $1.2 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.

Can Thinking Machines: Inkling Small (batch) process images?

Yes — Thinking Machines: Inkling Small (batch) accepts image input, so you can attach screenshots, photos or diagrams and ask questions about them.

Does Thinking Machines: Inkling Small (batch) support reasoning or thinking mode?

Yes. Thinking Machines: Inkling Small (batch) can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.

How can I use Thinking Machines: Inkling Small (batch) without an API key?

Open the CoreAI web app or the iOS/Android app, pick Thinking Machines: Inkling Small (batch) in the model selector, and chat — no API key, no per-token billing. One subscription covers Thinking Machines: Inkling Small (batch) and 300+ other models.

What are the best alternatives to Thinking Machines: Inkling Small (batch)?

The closest alternatives on CoreAI are Thinking Machines: Inkling Small, MiniMax: MiniMax M3, Mistral: Mistral Nemo — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.

Try Thinking Machines: Inkling Small (batch) Now

Chat with Thinking Machines: Inkling Small (batch) and 300+ other AI models — all in one app.

Use Web App Download App →