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

Copyright © 2026 NVIDIA Corporation

46 results for

Filters

  • Free Endpoint
    41
  • Partner Endpoint
    30
  • Download Available
    34
  • Image-to-Text
    8
  • Code Generation
    6
  • Synthetic Data Generation
    2
  • Deepinfra
    25
  • OpenRouter
    24
  • Together AI
    16
  • GMI Cloud
    13
  • Bitdeer
    7
  • NVIDIA
    15
  • Meta
    7
  • Mistral AI
    4
  • Google
    3
  • Minimaxai
    2
  • AI Engineer
    3
  • Developer
    2
  • Ml Engineer
    2
  • Application Developer
    1
  • Data Engineer
    1
  • AI And Machine Learning
    3
  • A100 SXM4 80GB
    7
  • A10G
    7
  • H100 80GB HBM3
    7
  • H100 NVL
    7
  • H200
    7
  • MONAI
    1
  • Nemotron
    1
  • TAO Toolkit
    1
    • NVIDIA
    Deprecation in 1dFree Endpoint

    nemotron-content-safety-reasoning-4b

    A context‑aware safety model that applies reasoning to enforce domain‑specific policies.
    Model
    NeMo Guardrails
    Items per page
    of 2 pages
    504K
    5mo

    Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants
    Skill
    Data Engineer
    1K
    1mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-nano-omni-30b-a3b-reasoning

    Nemotron 3 Nano Omni is an omni-modal reasoning model that understands images, video, speech, text.
    Model
    Image-to-Text
    8M
    2mo
    Mistral AI
    DownloadableFree Endpoint

    mistral-small-4-119b-2603

    Hybrid MoE model unifying instruct, reasoning, and coding with multimodal input and 256k context
    Model
    code generation
    11M
    4mo
    NVIDIA
    DownloadableFree Endpoint

    nvidia-nemotron-nano-9b-v2

    High‑efficiency LLM with hybrid Transformer‑Mamba design, excelling in reasoning and agentic tasks.
    Model
    thinking budget
    988K
    11mo
    ByteDance
    Deprecation in 13dFree Endpoint

    seed-oss-36b-instruct

    ByteDance open-source LLM with long-context, reasoning, and agentic intelligence.
    Model
    thinking budget
    1M
    10mo
    Stepfun-ai
    Deprecation in 13dFree Endpoint

    step-3.5-flash

    200B open-source reasoning engine with sparse MoE powering frontier agentic AI.
    Model
    Agentic
    10M
    5mo
    Google
    DownloadableFree Endpoint

    diffusiongemma-26b-a4b-it

    Diffusion-based 26B parameter LLM enabling parallel token generation for real-time text apps
    Model
    diffusion-llm
    4M
    1mo
    NVIDIA
    DownloadableFree Endpoint

    ising-calibration-1-35b-a3b

    Open VLM for quantum computer calibration chart understanding across a range of qubit modalities.
    Model
    Quantum
    442K
    3mo
    Mistral AI
    DownloadableFree Endpoint

    mistral-medium-3.5-128b

    A high performing model for text generation, coding and agentic use cases
    Model
    coding
    5M
    2mo
    Sarvamai
    DownloadableFree Endpoint

    sarvam-m

    Multilingual, hybrid-reasoning model optimized for Indian language tasks, programming, mathematical reasoning capabilities.
    Model
    coding
    436K
    11mo
    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
    Today
    Google
    DownloadableFree Endpoint

    gemma-4-31b-it

    Dense 31B model delivering frontier reasoning for coding, agentic workflows, and fine-tuning.
    Model
    reasoning
    6M
    3mo
    Minimaxai
    DownloadableFree Endpoint

    minimax-m2.7

    MiniMax M2.7 is a 230B-parameter text-to-text AI model excelling in coding, reasoning, and office tasks.
    Model
    coding
    16M
    3mo
    Minimaxai
    Free Endpoint

    minimax-m3

    MiniMax M3 Preview is a multimodal MoE vision-language model with strong reasoning, coding, and tool-calling capabilities.
    Model
    coding
    10M
    1mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-nano-30b-a3b

    Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
    Model
    MoE
    12M
    7mo
    NVIDIA
    DownloadableFree Endpoint

    nemotron-3-super-120b-a12b

    Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
    Model
    MoE
    60M
    4mo
    DeepSeek AI
    DownloadableFree Endpoint

    deepseek-v4-pro

    DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
    Model
    Moe
    8M
    2mo
    Moonshotai
    DeprecatedDownloadable

    kimi-k2.5

    1T multimodal MoE for high‑capacity video and image understanding with efficient inference.
    Model
    Multimodal
    5mo
    Moonshotai
    DownloadableFree Endpoint

    kimi-k2.6

    1T multimodal MoE for long-horizon coding, agentic tool use, and image/video understanding.
    Model
    Multimodal
    16M
    2mo
    Poolside
    Free Endpoint

    laguna-xs-2.1

    Efficient 33B MoE for local, long-horizon agentic coding and terminal tasks
    Model
    Agentic AI
    Today
    Z.ai
    DownloadableFree Endpoint

    glm-5.2

    GLM-5.2 is a flagship LLM for agentic workflows, coding, and long-horizon reasoning tasks.
    Model
    Agentic AI
    8M
    12d
    OpenAI
    DownloadableFree Endpoint

    gpt-oss-120b

    Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
    Model
    reasoning
    45M
    11mo
    OpenAI
    DownloadableFree Endpoint

    gpt-oss-20b

    Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
    Model
    reasoning
    18M
    11mo