Using Kosmos 2 on NVIDIA NIM

Implementation guide · Kosmos-2 · Microsoft Research

ProvisionedOpen Source

NVIDIA NIM exposes Kosmos 2 through model ID kosmos-2. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-05-19. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call kosmos-2 — see the documentation for request format.
  3. 3
    You'll be billed . See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

Capabilities

No model capability flags are currently sourced.

About Kosmos 2

Kosmos-2, developed by Microsoft Research, is an advanced multimodal large language model (MLLM) that enhances the capabilities of its predecessor, Kosmos-1. It features a Transformer-based architecture trained on the GrIT dataset of grounded image-text pairs, enabling it to understand and interact with both text and visual data. A key innovation is Kosmos-2's ability to ground language to the visual world, allowing for nuanced interaction with images by linking text to specific visual elements using location tokens.

Full model details →

Model Specs

Released2023-03-15
Parameters1.66B
Context2k
ArchitectureDecoder Only

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States