NVIDIA
Explore
Models
Blueprints
GPUs
Docs
⌘KCtrl+K
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2026 NVIDIA Corporation

5 results for

Filters (1)

  • Free Endpoint
    3
  • Partner Endpoint
    5
  • Download Available
    2
  • Launchable
    0
  • Enterprise
    0
  • Code Generation
    0
  • Digital Twin
    0
  • Drug Discovery
    0
  • Image Generation
    0
  • Image-to-Text
    0
  • Deep Infra
    3
  • Bitdeer AI
    3
  • GMI Cloud
    3
  • Together AI
    2
  • Lightning AI
    1
  • DeepSeek AI
    2
  • Mistral AI
    1
  • Moonshotai
    1
  • Qwen
    1
  • NVIDIA
    0
  • NVIDIA AI
    0
  • Reasoning
    • DeepSeek AI
    Downloadable

    deepseek-v4-pro

    DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
    Model
    Moe
    Items per page
    of 1 pages
    1.23M
    6d
    Qwen
    Downloadable

    qwen3-next-80b-a3b-thinking

    80B parameter AI model with hybrid reasoning, MoE architecture, support for 119 languages.
    Model
    Reasoning
    1.73M
    7mo
    DeepSeek AI
    Deprecation in 4dFree Endpoint

    deepseek-v3.2

    State-of-the-art 685B reasoning LLM with sparse attention, long context, and integrated agentic tools.
    Model
    long context
    8.76M
    4mo
    Mistral AI
    Deprecation in 11dFree Endpoint

    devstral-2-123b-instruct-2512

    State-of-the-art open code model with deep reasoning, 256k context, and unmatched efficiency.
    Model
    coding
    2.55M
    4mo
    Moonshotai
    Deprecation in 12dFree Endpoint

    kimi-k2-instruct

    State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities
    Model
    coding
    14.48M
    9mo