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 est le modèle de fondation multimodal à poids ouverts de Thinking Machines Lab. Il accepte des entrées texte, image et audio, génère du texte et peut être affiné sur Tinker pour des applications en aval.
Qu'est-ce que 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.
Que peut faire Inkling ?
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.
Cas d'utilisation
“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.
Questions fréquentes
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.
Informations rapides
- 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
Analyse du trafic de Inkling
Les données de trafic sont fournies à titre indicatif uniquement.
- Évaluation du domaine
- 77
Alternatives à Inkling
NobodyWho
nobodywho.ai
NobodyWho est un moteur d’inférence qui exécute des LLM en local et efficacement sur les appareils compatibles. Il s’adresse aux développeurs qui veulent réaliser des inférences hors ligne, traiter des entrées multimodales et créer des flux de travail locaux pour la voix et le texte, sans clés API.
通义实验室
tongyi.aliyun.com
通义实验室 est le portail de modèles et d’applications IA soutenu par Alibaba Cloud, avec Qwen, Wan, actualités et accès pour développeurs.
Ollama
ollama.com
Exécutez des modèles ouverts en local ou dans le cloud pour le code, l’automatisation, l’analyse et les agents.
MiniMax
minimaxi.com
MiniMax est une plateforme d’intelligence artificielle généraliste qui propose de grands modèles multimodaux, une plateforme ouverte pour les développeurs et des produits par abonnement pour les particuliers et les équipes. Elle convient aux utilisateurs qui ont besoin de coder, d’exécuter des tâches avec des agents, de traiter des contenus multimodaux et d’intégrer des applications natives de l’IA.
Arize AX
arize.com
Plateforme d’ingénierie IA pour tracer, évaluer et améliorer les agents et applications IA
Dify
dify.ai
Dify est un outil de création de workflows agentiques pour développer, déployer et gérer des agents autonomes, des pipelines RAG et des applications d’IA associées, avec des options cloud, auto-hébergées et d’entreprise.