Send a multi-turn conversation to a NVIDIA NIM language model and receive a completion. Supports all major open-source LLMs including Llama 3.1, Mistral, Gemma, Qwen, and more.

Generate text from a single prompt (simplified interface). Ideal for one-shot tasks like summarization, translation, extraction, or Q&A.

Convert text(s) into vector embeddings using NVIDIA NIM embedding models. Useful for semantic search, RAG, clustering, and similarity comparisons.

Rerank a list of passages by relevance to a query using NVIDIA NIM reranking models. Essential for RAG pipelines to improve retrieval quality.

Use NIM models with tool/function calling capabilities. The model will decide which function to call and with what arguments.

Get detailed information about a specific NVIDIA NIM model.

Generate images from text prompts using NVIDIA NIM image generation models (Stable Diffusion XL, SDXL Turbo, SD3, FLUX.1). Supports various resolutions, samplers, and schedulers. FLUX.1-schnell and FLUX.1-kontext-dev are available on the free NVIDIA AI Foundation tier. Can save generated images as PNG files to disk.

Analyze and describe images using NVIDIA NIM vision and multimodal models. Provide an image URL and a prompt/question to get detailed analysis, captioning, or visual Q&A.

Perform multimodal tasks combining text and images. Send a conversation with mixed text and image content to multimodal models for complex reasoning across modalities.

List available NVIDIA NIM models with detailed metadata for agent selection, optionally filtered by category (language, embedding, reranking, vision, code, multimodal, image_generation) and advanced filters.

Compare 2-5 models side-by-side across key decision factors: licensing, hardware requirements, benchmarks, capabilities, and use case tags. Returns structured comparison table.