Inkling Small
Fast and lightVisionToolsThinking Machines · 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.
It is part of Thinking Machines' Inkling line, offered in a full and a Small size with batch and free servings.
Facts and pricing
- Provider
- Thinking Machines
- Context window
- 524K tokens
- Input price
- 5.4 credits / 1M tokens ($0.45 raw)
- Output price
- 14.4 credits / 1M tokens ($1.20 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 1.20x margin. Raw prices shown per 1M tokens.
Try Inkling Small now
What Inkling Small is best for
- High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
- Very long documents and codebases: a 524K-token window fits entire books or repositories in one conversation
- Working with images: screenshots, charts, photos and scanned documents alongside text
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a fast and light model like Inkling Small:
- Summarize this article in five bullet points
- Rewrite this email to be shorter and friendlier
- Give me ten name ideas for a hiking newsletter
- Translate this paragraph to Spanish and keep the tone
Thinking Machines family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Inkling 2 Mini | 1.0M | 0.90 | 3.6 | November 2026 |
| Inkling 2 Small | 1.0M | 3.6 | 12.0 | November 2026 |
| Inkling Small | 524K | 5.4 | 14.4 | July 2026 |
| Inkling | 524K | 12.0 | 48.6 | July 2026 |
Model comparisons
- Claude Fable 5.2 vs Claude Fable 5.1
- Claude Opus 5.5 vs Claude Fable 5.2
- GPT-6 Astra vs Claude Fable 5.2
- Claude Opus 5.5 vs Claude Opus 5
Frequently asked questions
- What is Inkling Small?
- Inkling Small is an AI model by Thinking Machines. Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.
- How much does Inkling Small cost on Zeplik?
- Input tokens cost 5.4 credits per million and output tokens 14.4 credits per million (1 credit = $0.10; the raw provider rates are $0.45 and $1.20 per million). New accounts start with free credits.
- How long can a conversation with Inkling Small be?
- Inkling Small has a 524K-token context window (524,288 tokens), which covers the conversation plus any documents you attach.
- Does Inkling Small support images and tools?
- Inkling Small accepts image input and supports tool calling.
Related models
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).
Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total.
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from [Qwen3.8 27B](https://openrouter.ai/qwen/qwen3.8-27b) using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation.
Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following [Pixtral Large 2411](https://openrouter.ai/mistralai/pixtral-large-2411).
Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.
More you can do with Inkling Small
- 468 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Inkling Small or any model you pick.
- 1582 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.