Try NVIDIA NIM APIs

Skip to main content

Your Privacy Choices

Copyright © 2026 NVIDIA Corporation

18 results for

Filters

Free Endpoint

12

Partner Endpoint

8

Download Available

8

Launchable

2

Enterprise Blueprint

1

Use Case

Image-to-Text

5

Image Generation

1

Retrieval Augmented Generation

1

Text-to-Embedding

1

Text-to-Image

1

Inference Providers

Deepinfra

7

OpenRouter

5

GMI Cloud

3

Together AI

3

Bitdeer

1

Publisher

NVIDIA

6

Mistral AI

3

Meta

2

Black forest labs

1

Cyborg

1

Audience

AI Engineer

2

Developer

2

Hpc Developer

1

Ml Engineer

1

Security Engineer

1

Blueprint Type

NVIDIA AI

1

Domain

AI And Machine Learning

2

NIM Container GPUs

B200

2

GB200

1

H100 80GB HBM3

1

H200

1

L40S

1

Library

NeMo Megatron Bridge

1

Nemotron

1

Sort By

Free Endpoint

phi-4-multimodal-instruct

Cutting-edge open multimodal model exceling in high-quality reasoning from image and audio inputs.

Speech Recognition

Items per page

of 1 pages

244K

1y

DownloadableFree Endpoint

ministral-14b-instruct-2512

A general purpose VLM ideal for chat and instruction based use cases

language generation

4M

7mo

Free Endpoint

mistral-large-3-675b-instruct-2512

A state-of-the-art general purpose MoE VLM ideal for chat, agentic and instruction based use cases.

language generation

3M

7mo

Free Endpoint

llama-guard-4-12b

Multi-modal model to classify safety for input prompts as well output responses.

LLM Multimodal Safety

222K

1y

DownloadableFree Endpoint

kimi-k2.6

1T multimodal MoE for long-horizon coding, agentic tool use, and image/video understanding.

15M

2mo

Free Endpoint

nemotron-3-content-safety

Multilingual, multimodal model for detecting unsafe and toxic content.

230K

2mo

DownloadableFree Endpoint

nemotron-3.5-content-safety

Multilingual, multimodal model for detecting unsafe and toxic content.

2M

29d

Deprecation in 15dLaunchable

Cyborg Enterprise RAG

Securely extract, embed, and index multimodal data with encryption in-use for fast, accurate semantic search.

4mo

Black-forest-labs

Downloadable

FLUX.1-Kontext-dev

FLUX.1 Kontext is a multimodal model that enables in-context image generation and editing.

4K

10mo

Free Endpoint

llama-4-maverick-17b-128e-instruct

A general purpose multimodal, multilingual 128 MoE model with 17B parameters.

language generation

20M

11mo

Downloadable

llama-nemotron-embed-vl-1b-v2

Multimodal question-answer retrieval representing user queries as text and documents as images.

8M

4mo

DownloadableFree Endpoint

mistral-small-4-119b-2603

Hybrid MoE model unifying instruct, reasoning, and coding with multimodal input and 256k context

code generation

13M

3mo

DownloadableFree Endpoint

qwen3.5-122b-a10b

122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.

10M

3mo

DownloadableFree Endpoint

step-3.7-flash

A sparse MoE multimodal reasoning model good for enterprise, agentic and coding tasks.

4M

1mo

Free Endpoint

minimax-m3

MiniMax M3 Preview is a multimodal MoE vision-language model with strong reasoning, coding, and tool-calling capabilities.

6M

19d

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.

904

1mo

General

LaunchableEnterprise

Build an Enterprise RAG Pipeline Blueprint

Power fast, accurate semantic search across multimodal enterprise data with NVIDIA’s RAG Blueprint—built on NeMo Retriever and Nemotron models—to connect your agents to trusted, authoritative sources of knowledge.

4mo

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough

822

26d