Multimodal input support
Inkling is a multimodal autoregressive transformer that accepts text, images, and audio, while producing text outputs. The model card says it is intended for English and other languages, as well as multiple coding languages.
Inkling
Freemium
Inkling is Thinking Machines Lab’s open-weights multimodal foundation model. It accepts text, image, and audio inputs, generates text, and supports fine-tuning on Tinker for downstream applications.
What is Inkling?
Inkling is Thinking Machines Lab’s open-weights multimodal model. It is presented as a general-purpose foundation model that accepts text, image, and audio inputs and generates text outputs, with support for English, other languages, and multiple coding languages.
The model card describes Inkling as a 66-layer decoder-only transformer with sparse Mixture-of-Experts routing, 975B total parameters, 41B active, and a context window of up to 1M tokens. Thinking Machines positions it as a customizable base model for developers building conversational systems, agentic workflows, coding tools, and retrieval-augmented applications.
Inkling is distributed with open weights under Apache 2.0, available through Hugging Face, and can be fine-tuned on Tinker. The launch materials also point to Inkling-Small as a lighter-weight preview in the same family, but the source page emphasizes Inkling as the main release.
What can Inkling do?
Sparse MoE architecture
The model uses a sparse Mixture-of-Experts architecture with 975B total parameters and 41B active parameters. According to the model card, each token is routed to 6 of 256 experts, plus 2 shared experts.
Long-context processing
Inkling supports a context window of up to 1M tokens, which makes it suitable for long-document and long-conversation workflows.
Controllable reasoning effort
The launch post says Inkling balances cost and performance through controllable thinking effort. That makes it a base model that can be used with different levels of reasoning effort depending on the task.
Fine-tuning via Tinker
Inkling is available for fine-tuning on Tinker, and the Tinker product page describes training through four functions: forward_backward, optim_step, sample, and save_state.
Multiple access paths
The model card says the weights are available through Hugging Face, and the model is also accessible via Tinker and third-party inference providers.
Use Cases
“Multimodal assistants”
Developers can build chatbots or assistant-style products that need to respond to text prompts and also interpret images or audio in the same session.
“Developer applications”
Teams working on coding copilots, tool-using agents, or retrieval-augmented systems can use Inkling as a general-purpose base model for downstream tuning and integration.
“Model customization”
Researchers and product teams can fine-tune the open weights on Tinker to adapt the model to a specific behavior or workflow, such as a custom response style or domain task.
“Long-context workflows”
Applications that must process long documents, lengthy conversations, or extended context across multiple turns can take advantage of the model’s 1M-token context window.
“Deployment planning”
Organizations evaluating open-weights deployment options can use the model card’s checkpoint and hardware guidance to plan inference on their own systems or through supported providers.
Frequently Asked Questions
How is Inkling distributed?
Inkling is available as an open-weights model, with the weights offered through Hugging Face and the model also accessible via Tinker and third-party inference providers. The announcement and model card indicate it is intended for downstream developers rather than a consumer chat app.
What can Inkling take as input and output?
The model card says Inkling accepts text, image, and audio inputs and generates text outputs. It is designed for general-purpose conversational use, instruction-following, coding, agentic workflows, and retrieval-augmented generation systems.
How does fine-tuning work with Inkling?
Tinker is the training API used to fine-tune Inkling. The model card says Inkling is available for fine-tuning on Tinker, and the launch post describes using Tinker to write, run, and evaluate a self-finetuning job before updating the active weights.
What are Inkling's core model characteristics?
The model card describes Inkling as a 66-layer decoder-only transformer with sparse Mixture-of-Experts routing. It has 975B total parameters, 41B active, and supports a context window of up to 1M tokens.
Is there public pricing information for Inkling or Tinker?
The source materials do not provide pricing information. The pricing URL currently returns a 404 page not found.
Quick Facts
- Category
- Open-weights multimodal model
- Provider
- Thinking Machines Lab, Inc.
- Release date
- July 15, 2026
- License
- Apache 2.0
- Inputs
- Text, image, audio
- Outputs
- Text
Inkling Traffic Analysis
Traffic data is for reference only.
- Domain Rating
- 77
Inkling Alternatives
NobodyWho
nobodywho.ai
NobodyWho is an inference engine for running LLMs locally and efficiently on supported devices. It’s for developers seeking offline model inference, multimodal inputs, and local speech and text workflows without API keys.
MiniMax
minimax.io
MiniMax is a global AI foundation model platform offering multimodal models, AI-native products, and API or subscription access for people, teams, enterprises, and developers.
MiniMax
minimaxi.com
MiniMax is a general-purpose AI platform offering multimodal large models, an open platform for developers, and subscription products for individuals and teams. It suits users building with code, agent tasks, multimodal processing, and AI-native applications.
Ludwig
ludwig.ai
Open-source declarative deep learning framework for training, fine-tuning, and deploying models from one YAML config.
AI Toolkit
tiptap.dev
AI Toolkit helps developers build document-aware AI agents that edit rich-text content in place while keeping changes reviewable. It supports server-side workflows, real-time collaboration, and backend processing without requiring a Tiptap Editor session.
Poolside
poolside.ai
Poolside is a foundation model and agent platform for secure, governed software development across terminal, IDE, browser, and headless workflows.