[ { "slug": "ansys/fluent", "display_name": "fluent", "description": "Run computational-fluid dynamics (CFD) simulations", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "ansys" }, { "slug": "arc/evo2-40b", "display_name": "evo2-40b", "description": "Evo 2 is a biological foundation model that is able to integrate information over long genomic sequences while retaining sensitivity to single-nucleotide changes.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "arc" }, { "slug": "arc/evo2-40b-forward", "display_name": "evo2-40b-forward", "description": "Evo 2 is a biological foundation model that is able to integrate information over long genomic sequences while retaining sensitivity to single-nucleotide changes.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "arc" }, { "slug": "arc/evo2-7b-forward", "display_name": "evo2-7b-forward", "description": "Evo 2 is a biological foundation model that is able to integrate information over long genomic sequences while retaining sensitivity to single-nucleotide changes.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "arc" }, { "slug": "baidu/paddleocr", "display_name": "paddleocr", "description": "Model for table extraction that receives an image as input, runs OCR on the image, and returns the text within the image and its bounding boxes.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "baidu" }, { "slug": "black-forest-labs/flux_1-dev", "display_name": "FLUX.1-dev", "description": "FLUX.1 is a state-of-the-art suite of image generation models", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "black-forest-labs" }, { "slug": "black-forest-labs/flux_1-kontext-dev", "display_name": "FLUX.1-Kontext-dev", "description": "FLUX.1 Kontext is a multimodal model that enables in-context image generation and editing.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "black-forest-labs" }, { "slug": "black-forest-labs/flux_1-schnell", "display_name": "FLUX.1-schnell", "description": "FLUX.1-schnell is a distilled image generation model, producing high quality images at fast speeds", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "black-forest-labs" }, { "slug": "black-forest-labs/flux_2-klein-4b", "display_name": "flux.2-klein-4b", "description": "FLUX.2-klein-4B is a distilled image generation and editing model, producing outputs at lighting speed", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "black-forest-labs" }, { "slug": "black-forest-labs/flux-3-image-klein", "display_name": "flux-3-image-klein", "description": "FLUX 3 Image Klein is a state-of-the-art open-weight image generation and editing model", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "black-forest-labs" }, { "slug": "cadence/fidelity", "display_name": "fidelity", "description": "Run computational-fluid dynamics (CFD) simulations", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "cadence" }, { "slug": "cadence/spectre-x", "display_name": "spectre-x", "description": "Run large-scale electronics and chip design verification simulations", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "cadence" }, { "slug": "colabfold/msa-search", "display_name": "msa-search", "description": "Generates a multiple sequence alignment from a query sequence and a protein sequence database search.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "colabfold" }, { "slug": "deepseek-ai/deepseek-v4.1-flash", "display_name": "deepseek-v4.1-flash", "description": "552B MoE, 8B active params with native multimodal support and lower API cost using smaller KV cache", "context_window": 1048576, "max_output_tokens": 4096, "supports_tools": true, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "direct", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "deepseek-ai" }, { "slug": "google/diffusiongemma-26b-a4b-it", "display_name": "diffusiongemma-26b-a4b-it", "description": "Diffusion-based 26B parameter LLM enabling parallel token generation for real-time text apps", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "google" }, { "slug": "google/gemma-4-31b-it", "display_name": "gemma-4-31b-it", "description": "Dense 31B model delivering frontier reasoning for coding, agentic workflows, and fine-tuning.", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "google" }, { "slug": "google/google-paligemma", "display_name": "paligemma", "description": "Vision language model adept at comprehending text and visual inputs to produce informative responses", "context_window": 8192, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "fast", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "google" }, { "slug": "ipd/proteinmpnn", "display_name": "proteinmpnn", "description": "ProteinMPNN is a deep learning model for predicting amino acid sequences for protein backbones.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "ipd" }, { "slug": "ipd/rfd4-proteina", "display_name": "rfd4-proteina", "description": "A unified generative model for protein, enzyme, binder and antibody design.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "ipd" }, { "slug": "ipd/rfdiffusion", "display_name": "rfdiffusion", "description": "A generative model of protein backbones for protein binder design.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "ipd" }, { "slug": "meta/llama-3.2-11b-vision-instruct", "display_name": "llama-3.2-11b-vision-instruct", "description": "Cutting-edge vision-language model exceling in high-quality reasoning from images.", "context_window": 131072, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "meta" }, { "slug": "meta/llama-3.2-90b-vision-instruct", "display_name": "llama-3.2-90b-vision-instruct", "description": "Cutting-edge vision-Language model exceling in high-quality reasoning from images.", "context_window": 131072, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "meta" }, { "slug": "meta/llama-guard-4-12b", "display_name": "llama-guard-4-12b", "description": "Multi-modal model to classify safety for input prompts as well output responses.", "context_window": 163840, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "meta" }, { "slug": "meta/muse-glimmer-30b", "display_name": "muse-glimmer-30b", "description": "Muse Glimmer 30B is a multimodal reasoning model accepting text and images, with native tool-calling and separate reasoning output.", "context_window": 131072, "max_output_tokens": 4096, "supports_tools": true, "supports_thinking": true, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "direct", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "reasoning", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "meta" }, { "slug": "microsoft/trellis", "display_name": "TRELLIS", "description": "MSFT TRELLIS is a 3D AI model that generates high-quality 3D assets from text or image inputs.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "microsoft" }, { "slug": "minimaxai/minimax-m3.1-flash", "display_name": "minimax-m3.1-flash", "description": "MiniMax-M3.1-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, computer use, and cybersecurity.", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "minimaxai" }, { "slug": "mistralai/mistral-large-4-1t-a52b", "display_name": "Mistral Large 4", "description": "Mistral Large 4 from Mistral AI, a 1T-total / 52B-active granular MoE for text and image input with reasoning, function calling and structured outputs, served in NVFP4 with DSpark speculative decoding.", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "mistralai" }, { "slug": "mit/boltz2", "display_name": "Boltz-2", "description": "Predict complex structures using Boltz-2.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "mit" }, { "slug": "mit/diffdock", "display_name": "diffdock", "description": "Predicts the 3D structure of how a molecule interacts with a protein.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "mit" }, { "slug": "nvidia/active-speaker-detection", "display_name": "Active Speaker Detection", "description": "Detect and track speaker identities across video frames.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/bevformer", "display_name": "bevformer", "description": "Advanced transformer for multi-frame bird's-eye-view 3D perception in autonomous driving.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/bnr", "display_name": "Background Noise Removal", "description": "Removes unwanted noises from audio improving speech intelligibility.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/body-pose", "display_name": "3D Body Pose", "description": "Estimate 3D human body pose and skeleton from video input.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/canary-1b-asr", "display_name": "canary-1b-asr", "description": "Multi-lingual model supporting speech-to-text recognition and translation.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/conformer-ctc-asr", "display_name": "conformer-ctc-asr", "description": "Automatic speech recognition model that transcribes speech in lower case Spanish with record-setting accuracy and performance", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/cosmos-transfer2_5-2b", "display_name": "cosmos-transfer2.5-2b", "description": "Generates physics-aware video world states for physical AI development using text prompts and multiple spatial control inputs derived from real-world data or simulation.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/cosmos3-nano", "display_name": "cosmos3-nano", "description": "Generates images, videos and action predictions from text, visual inputs and spatial controls, with mandatory input screening and visual SynthID watermarking.", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/cosmos3-nano-reasoner", "display_name": "cosmos3-nano-reasoner", "description": "Vision language model that excels in understanding the physical world using structured reasoning on videos or images.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": true, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "reasoning", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/eyecontact", "display_name": "eyecontact", "description": "Estimate gaze angles of a person in a video and redirect to make it frontal.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/fourcastnet", "display_name": "fourcastnet", "description": "FourCastNet predicts global atmospheric dynamics of various weather / climate variables.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/genmol-generate", "display_name": "genmol", "description": "Fragment-Based Molecular Generation by Discrete Diffusion.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/ising-calibration-1-35b-a3b", "display_name": "ising-calibration-1-35b-a3b", "description": "Open VLM for quantum computer calibration chart understanding across a range of qubit modalities.", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/ising-calibration-1.5-31b", "display_name": "ising-calibration-1.5-31b", "description": "NVIDIA-Ising-Calibration-1.5 is a dense multimodal vision-language model built on Gemma 4 31B. It analyzes quantum computing calibration experiment plots and generates structured technical text.", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/kumo-relational", "display_name": "Kumo Relational", "description": "A relational foundation model for prediction over structured, multi-table data.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/kumo-tabular", "display_name": "Kumo Tabular", "description": "A tabular in-context learning model for classification and regression over structured tables.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/lipsync", "display_name": "LipSync", "description": "Generative lip dubbing that syncs lips in a video to input audio.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/llama-3_1-nemoguard-8b-content-safety", "display_name": "llama-3.1-nemoguard-8b-content-safety", "description": "Leading content safety model for enhancing the safety and moderation capabilities of LLMs", "context_window": 131072, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/llama-3_1-nemoguard-8b-topic-control", "display_name": "llama-3.1-nemoguard-8b-topic-control", "description": "Topic control model to keep conversations focused on approved topics, avoiding inappropriate content.", "context_window": 131072, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/llama-3_1-nemotron-safety-guard-8b-v3", "display_name": "llama-3.1-nemotron-safety-guard-8b-v3", "description": "Leading multilingual content safety model for enhancing the safety and moderation capabilities of LLMs", "context_window": 8192, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "fast", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/llama-nemotron-embed-vl-1b-v2", "display_name": "llama-nemotron-embed-vl-1b-v2", "description": "Multimodal question-answer retrieval representing user queries as text and documents as images.", "context_window": 16384, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/llama-nemotron-rerank-vl-1b-v2", "display_name": "llama-nemotron-rerank-vl-1b-v2", "description": "GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.", "context_window": 10240, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/magpie-tts-multilingual", "display_name": "magpie-tts-multilingual", "description": "Natural and expressive voices in multiple languages. For voice agents and brand ambassadors.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/magpie-tts-zeroshot", "display_name": "magpie-tts-zeroshot", "description": "Expressive and engaging text-to-speech, generated from a short audio sample.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/megatron-1b-nmt", "display_name": "megatron-1b-nmt", "description": "Enable smooth global interactions in 36 languages.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/molmim-generate", "display_name": "molmim", "description": "MolMIM performs controlled generation, finding molecules with the right properties.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemoguard-jailbreak-detect", "display_name": "nemoguard-jailbreak-detect", "description": "Industry leading jailbreak classification model for protection from adversarial attempts", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemoretriever-ocr", "display_name": "nemoretriever-ocr", "description": "Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3_5-embed-1b", "display_name": "nemotron-3.5-embed-1b", "description": "1B multimodal embedding model for text and document-image retrieval in RAG applications.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3_5-embed-8b", "display_name": "nemotron-3.5-embed-8b", "description": "8B multimodal embedding model for text and document-image retrieval in RAG applications.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3_5-rerank-8b", "display_name": "nemotron-3.5-rerank-8b", "description": "8B multimodal reranking model that scores how relevant a text or document-image passage is to a query.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3-embed-1b", "display_name": "nemotron-3-embed-1b", "description": "1B embedding model for semantic search, retrieval, and RAG applications.", "context_window": 32768, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "display_name": "nemotron-3-nano-omni-30b-a3b-reasoning", "description": "Nemotron 3 Nano Omni is an omni-modal reasoning model that understands images, video, speech, text.", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": true, "supports_thinking": true, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "direct", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "reasoning", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3-ultra-550b-a55b", "display_name": "nemotron-3-ultra-550b-a55b", "description": "Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more", "context_window": 1048576, "max_output_tokens": 4096, "supports_tools": true, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "direct", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3.5-bolt-e4b", "display_name": "Nemotron 3.5 Bolt E4B", "description": "Compact text model for reasoning, tool calling, and agentic chat.", "context_window": 65536, "max_output_tokens": 4096, "supports_tools": true, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "direct", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3.5-content-safety", "display_name": "nemotron-3.5-content-safety", "description": "Multilingual, multimodal model for detecting unsafe and toxic content.", "context_window": 131072, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3.5-lightning-30b-a3b", "display_name": "nemotron-3.5-lightning-30b-a3b", "description": "Fastest 30B A3B MoE model with leading domain accuracy for specialized agentic tasks", "context_window": 1048576, "max_output_tokens": 4096, "supports_tools": true, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "direct", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": true, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3.5-parse", "display_name": "nemotron-3.5-parse", "description": "Extract text, tables, and document layout from page images.", "context_window": 9000, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-3.5-super-vl-120b-a12b", "display_name": "nemotron-3.5-super-vl-120b-a12b", "description": "Nemotron 3.5 Super early-access reasoning model for agentic, coding, tool-calling, and multimodal workloads", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": true, "supports_thinking": true, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "direct", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "reasoning", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-asr-streaming", "display_name": "nemotron-asr-streaming", "description": "Real-time speech recognition for English", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-graphic-elements-v1", "display_name": "nemotron-graphic-elements-v1", "description": "Model for object detection, fine-tuned to detect charts, tables, and titles in documents.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-ocr-v1", "display_name": "nemotron-ocr-v1", "description": "Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-ocr-v2", "display_name": "nemotron-ocr-v2", "description": "Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-page-elements-v3", "display_name": "nemotron-page-elements-v3", "description": "Model for object detection, fine-tuned to detect charts, tables, and titles in documents.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-parse", "display_name": "nemotron-parse", "description": "Cutting-edge vision-language model exceling in retrieving text and metadata from images.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-parse-2.0", "display_name": "nemotron-parse-2.0", "description": "Cutting-edge vision-language model excelling in retrieving text and metadata from images.", "context_window": 9000, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-table-structure-v1", "display_name": "nemotron-table-structure-v1", "description": "Model for object detection, fine-tuned to detect charts, tables, and titles in documents.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nemotron-voicechat", "display_name": "nemotron-voicechat", "description": "Nemotron 3 Voicechat", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/nvidia-cuopt", "display_name": "cuopt", "description": "World-record accuracy and performance for complex route optimization.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/parakeet-1_1b-rnnt-multilingual-asr", "display_name": "parakeet-1.1b-rnnt-multilingual-asr", "description": "High accuracy and optimized performance for transcription in 25 languages", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/parakeet-ctc-0_6b-asr", "display_name": "parakeet-ctc-0.6b-asr", "description": "State-of-the-art accuracy and speed for English transcriptions.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/parakeet-ctc-0_6b-es", "display_name": "parakeet-ctc-0.6b-es", "description": "Accurate and optimized Spanish English transcriptions with punctuation and word timestamps.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/parakeet-ctc-0_6b-vi", "display_name": "parakeet-ctc-0.6b-vi", "description": "Accurate and optimized Vietnamese-English transcriptions with punctuation and word timestamps.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/parakeet-ctc-0_6b-zh-cn", "display_name": "parakeet-ctc-0.6b-zh-cn", "description": "Record-setting accuracy and performance for Mandarin English transcriptions.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/parakeet-ctc-0_6b-zh-tw", "display_name": "parakeet-ctc-0.6b-zh-tw", "description": "Record-setting accuracy and performance for Mandarin Taiwanese English transcriptions.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/parakeet-ctc-1_1b-asr", "display_name": "parakeet-ctc-1.1b-asr", "description": "Record-setting accuracy and performance for English transcription.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/parakeet-tdt-0_6b", "display_name": "parakeet-tdt-0.6b", "description": "Multilingual ASR across 25 European languages with punctuation, capitalization, and word timestamps", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/parakeet-tdt-0_6b-v2", "display_name": "parakeet-tdt-0.6b-v2", "description": "Accurate and optimized English transcriptions with punctuation and word timestamps", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/qwen-image-edit-nvpcb-ovsl2sl", "display_name": "qwen-image-edit-nvpcb-ovsl2sl", "description": "An image edit model specialized for Omniverse synthetic to photographic solder-light style captured at NVIDIA PCB inspection stations", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/relighting", "display_name": "Relighting", "description": "Re-illuminate people in video to match target lighting from a 360 HDRI environment map.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/riva-translate-1_6b", "display_name": "riva-translate-1.6b", "description": "Enable smooth global interactions in 36 languages.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/riva-translate-4b-instruct-v2", "display_name": "riva-translate-4b-instruct-v2", "description": "Translation model in 37 languages with few-shots example prompts capability.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/sparsedrive", "display_name": "sparsedrive", "description": "End-to-end autonomous driving stack integrating perception, prediction, and planning with sparse scene representations for efficiency and safety.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/streampetr", "display_name": "streampetr", "description": "StreamPETR offers efficient 3D object detection for autonomous driving by propagating sparse object queries temporally.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/studiovoice", "display_name": "Studio Voice", "description": "Enhance input speech recorded with low-quality microphones in noisy or reverberant environments, producing studio-quality speech.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/synthetic-video-detector", "display_name": "synthetic-video-detector", "description": "NVIDIA Synthetic Video Detector is an AI-powered micro-service for detecting AI‑generated (synthetic) videos.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "nvidia/vsr", "display_name": "Video Super Resolution NIM", "description": "Upscale encoded or ST 2110 video to higher resolutions with NVIDIA Video Super Resolution.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "nvidia" }, { "slug": "openai/gpt-oss-20b", "display_name": "gpt-oss-20b", "description": "Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math", "context_window": 131072, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": true, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "reasoning", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "openai" }, { "slug": "openai/whisper-large-v3", "display_name": "whisper-large-v3", "description": "Robust Speech Recognition via Large-Scale Weak Supervision.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "openai" }, { "slug": "openfold/openfold2", "display_name": "openfold2", "description": "Predicts the 3D structure of a protein from its amino acid sequence, multiple sequence alignments, and templates.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "openfold" }, { "slug": "openfold/openfold3", "display_name": "openfold3", "description": "OpenFold3 is a third-generation biomolecular foundation model that predicts the three-dimensional structures of molecular complexes (proteins, DNA, RNA, ligands)", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "openfold" }, { "slug": "poolside/laguna-xs-2.1", "display_name": "laguna-xs-2.1", "description": "Efficient 33B MoE for local, long-horizon agentic coding and terminal tasks", "context_window": 262144, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "poolside" }, { "slug": "qwen/qwen-image", "display_name": "qwen-image", "description": "Qwen-Image is a text-to-image foundation model with advanced multilingual text rendering.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "qwen" }, { "slug": "qwen/qwen-image-edit", "display_name": "qwen-image-edit", "description": "Qwen-Image-Edit is an image editing model with multilingual text editing and strong subject consistency.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "qwen" }, { "slug": "resembleai/chatterbox-multilingual-tts", "display_name": "chatterbox-multilingual-tts", "description": "Natural and expressive voices in 23 languages. For voice agents and brand ambassadors.", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "resembleai" }, { "slug": "siemens/star-ccm", "display_name": "simcenter-star-ccm+", "description": "Run computational-fluid dynamics (CFD) simulations", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": false, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "siemens" }, { "slug": "stabilityai/stable-diffusion-3_5-large", "display_name": "stable-diffusion-3.5-large", "description": "Stable Diffusion 3.5 is a popular text-to-image generation model", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "stabilityai" }, { "slug": "stepfun-ai/step-5-preview", "display_name": "Step 5 Preview", "description": "Preview of StepFun's Step 5: ~600B-total / 27B-active multimodal MoE (text and image in, text out) with 1M context, reasoning and tool calling, served in NVFP4.", "context_window": 1048576, "max_output_tokens": 4096, "supports_tools": true, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "direct", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "stepfun-ai" }, { "slug": "wan-ai/wan2.2-animate-2-14b", "display_name": "wan2.2-animate-2-14b", "description": "Wan2.2-Animate-2 is a novel end-to-end character animation framework", "context_window": 4096, "max_output_tokens": 4096, "supports_tools": false, "supports_thinking": false, "supports_vision": true, "supports_audio": true, "default_temperature": 0.2, "tool_mode": "unsupported", "input_modalities": [ "text", "audio", "image", "video" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "wan-ai" }, { "slug": "z-ai/glm-5-3-flash", "display_name": "glm-5-3-flash", "description": "Multimodal 320B-total / 18B-active MoE with hybrid KDA and sparse MLA attention, native FP8 weights, reasoning and tool calling.", "context_window": 1048576, "max_output_tokens": 4096, "supports_tools": true, "supports_thinking": false, "supports_vision": true, "supports_audio": false, "default_temperature": 0.2, "tool_mode": "direct", "input_modalities": [ "text", "image" ], "truncation_policy": "truncate", "service_tier": "standard", "multi_agent_version": 1, "auto_compact_threshold_percent": 75, "instructions_template": null, "requires_auth": true, "is_default": false, "originator": "z-ai" } ]