Inkling
Inkling is an open-weights, multimodal, Mixture-of-Experts model with controllable reasoning effort, available for fine-tuning.
Inkling is an open-weights, multimodal, Mixture-of-Experts transformer model with 975B total parameters and 41B active. It supports a 1M token context window and was pretrained on 45 trillion tokens of text, images, audio, and video. It offers controllable reasoning effort, balancing performance with token efficiency, and is available for fine-tuning on Tinker.
Freemium
How to use Inkling?
Inkling can be accessed via the Inkling Playground on Tinker for interactive chat, or fine-tuned for specific tasks using the Tinker platform. Its full weights are available on Hugging Face for custom deployments. It integrates with various platforms like Together AI, Fireworks, and Modal for API access and inference.
Inkling 's Core Features
Inkling 's Use Cases
Inkling 's Pricing
Inkling
$0.000005/token
Inkling is available on Tinker with context length options of 64K and 256K tokens. A 50% discount is offered for a limited time.
Inkling 's FAQ
Most impacted jobs
AI Researcher
Machine Learning Engineer
Software Developer
Data Scientist
AI Product Manager
