Inkling Small
StandardThinking Machines Lab's smaller, more efficient open-weight multimodal model, with 12B active parameters out of 276B total.
1M-token context with image and audio understanding and configurable thinking effort. Suited to reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation at a fraction of Inkling's cost.
▼
Inkling Small is somewhat expensive at $0.45/M tokens input and $1.20/M tokens output. Cached input reads are priced at $0.10/M tokens, making repeated context cheaper. The model supports vision/image input, audio input, extended reasoning, a 524K context window.
Benchmarks
Specifications
Performance
Providers
Misc
Compare with
Frequently Asked Questions about Inkling Small▼
When was Inkling Small released?
▼
Inkling Small was released on July 30, 2026.
Who created Inkling Small?
▼
Inkling Small was created by Thinking Machines Lab.
How much does Inkling Small cost?
▼
Inkling Small costs $0.45/M input tokens and $1.20/M output tokens.
What is Inkling Small API pricing?
▼
The Inkling Small API is priced at $0.45 per million input tokens and $1.20 per million output tokens. You can access Inkling Small through idapt.app alongside 200+ other AI models in one workspace.
Is Inkling Small a reasoning model?
▼
Yes, Inkling Small is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.
Does Inkling Small support image or vision input?
▼
Yes, Inkling Small supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.
Does Inkling Small support audio?
▼
Yes, Inkling Small supports audio input, allowing it to process and respond to voice and audio files.
What is the context window of Inkling Small?
▼
Inkling Small has a context window of 524K tokens, meaning it can process approximately 393,216 words of context at once.
Is Inkling Small open source?
▼
Inkling Small is a proprietary model developed by Thinking Machines Lab. The model weights and training data are not publicly available.
What is Inkling Small good at?
▼
Based on benchmark data, Inkling Small excels at: visual analysis and image understanding. It is Thinking Machines Lab's capable model suitable for a wide range of tasks.
Where can I use Inkling Small?
▼
You can chat with Inkling Small on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Inkling Small through Thinking Machines Lab's own API or platform.