Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2026 NVIDIA Corporation

2 results for

Filters (1)

  • Free Endpoint
    2
  • Partner Endpoint
    2
  • Download Available
    2
  • Developer Example
    0
  • Enterprise Blueprint
    0
  • Launchable
    0
  • Image Generation
    0
  • Text-to-Image
    0
  • Image-to-Text
    0
  • Synthetic Data Generation
    0
  • Optical Character Recognition
    0
  • OpenRouter
    2
  • Deepinfra
    1
  • Together AI
    1
  • GMI Cloud
    1
  • Vultr
    0
  • Qwen
    1
  • Thinkingmachines
    1
  • NVIDIA
    0
  • Black forest labs
    0
  • Google
    0
  • Developer
    0
  • AI Engineer
    0
  • Ml Engineer
    0
  • Application Developer
    0
  • Platform Engineer
    0
  • NVIDIA AI
    0
  • NVIDIA Isaac GR00T
    0
  • NVIDIA Omniverse
    0
  • AI And Machine Learning
    0
  • Physical AI
    0
  • Developer Tools
    0
  • Infrastructure
    0
  • A100 PG509 200
    0
  • A100 SXM4 80GB
    0
  • A10G
    0
  • B200
    0
  • H100 80GB HBM3
    0
  • TAO Toolkit
    0
  • Jetson
    0
  • DeepStream SDK
    0
  • Physical AI Dataset
    0
  • NeMo Retriever
    0
  • text-to-text
    • Thinkingmachines
    DownloadableFree Endpoint

    inkling

    Inkling is a multimodal (text + image) reasoning model from Thinking Machines — a Mamba-hybrid, 256-expert Mixture-of-Experts architecture with tool use and switchable reasoning.
    Model
    text-to-text
    2d
    Items per page
    of 1 pages
    Qwen
    DownloadableFree Endpoint

    qwen3.5-122b-a10b

    122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
    Model
    tool calling
    15M
    4mo