Inference Endpoints
Catalog
Deploy
F
Log In
Model Catalog
Collection
Thinking Machines Lab
Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.
Inference Task
All Tasks
Price
$ 0 - 40 / hour
0
0.1
0.5
1
5
40
Deploy On
ALL
CPU
GPU
INF2
Inference Engine
All
Llama.cpp
TEI
vLLM
SGLang
License
All Licenses
Hub Models
Browse All Models
2 items
Order by:
Most Recent
thinkingmachines
Inkling-Small-NVFP4
Any-to-Any
SGLang Engine
Apache 2.0 License
GPU
1x Nvidia RTX PRO 6000 Blackwell
$
2.75
thinkingmachines
Inkling-NVFP4
Image-Text-to-Text
SGLang Engine
Apache 2.0 License
GPU
8x Nvidia H200
$
40