Thinking Machines models

Thinking Machines ships the Inkling models. Zeplik carries both sizes — Inkling and the lighter Inkling Small — each with batch and free servings.

Ask a Thinking Machines model now

All 4 Thinking Machines models

Pricing at a glance

Frequently asked questions

Which Thinking Machines models can I use on Zeplik?

Zeplik carries 4 Thinking Machines models: Inkling Small (free), Inkling Small, Inkling (free) and Inkling. They all run in the same chat, so you do not need a separate Thinking Machines account or API key.

How much do Thinking Machines models cost on Zeplik?

Output tokens run from 14.4 to 48.6 credits per million depending on which Thinking Machines model you pick (raw provider rates $1.20 to $4.05 per million). 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin.

Which Thinking Machines model has the largest context window?

Inkling Small (free), at 1.0M tokens (1,048,576). The context window covers the conversation plus any documents you attach.

Do Thinking Machines models support images and tool calling?

All 4 accept image input, and all of them support tool calling.

Do I need a paid plan to use Thinking Machines models on Zeplik?

All 4 need a paid plan (Plus or above). Usage is then billed in credits from your monthly allowance.

What is the newest Thinking Machines model on Zeplik?

Inkling Small (free), released July 2026. Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.

Other providers

• OpenAI (100)
• Qwen (53)
• Google (42)
• Anthropic (29)
• Mistral (26)
• Z.ai (18)
• DeepSeek (15)
• NVIDIA (11)
• All models