Visual Models APIsOverview Models black-forest-labs ModelEndpointblack-forest-labs / flux.1-devInfer (flux.1-dev)black-forest-labs / flux.1-schnellInfer (flux.1-schnell)black-forest-labs / flux.2-klein-4bInfer (flux.2-klein-4b) google ModelEndpointgoogle / gemma-3-27b-itRequest response from the model (gemma-3-27b-it)google / gemma-3n-e2b-itRequest response from the model (gemma-3n-e2b-it)google / gemma-3n-e4b-itRequest response from the model (gemma-3n-e4b-it)google / gemma-4-31b-itRequest response from the model (google-gemma-4-31b-it) hive ModelEndpointhive / ai-generated-image-detectionRequest response from the model (ai-generated-image-detection)hive / deepfake-image-detectionInfer (deepfake-image-detection) meta ModelEndpointmeta / llama-guard-4-12bRequest response from the model (llama-guard-4-12b) microsoft ModelEndpointmicrosoft / phi-4-multimodal-instructRequest response from the model (phi-4-multimodal-instruct)microsoft / trellisInfer (trellis) mistralai ModelEndpointmistralai / mistral-large-3-675b-instruct-2512Request response from the model (mistral-large-3-675b-instruct-2512)mistralai / ministral-14b-instruct-2512Request response from the model (ministral-14b-instruct-2512)mistralai / mistral-medium-3-instructRequest response from the model (mistral-medium-3-instruct)mistralai / mistral-medium-3.5-128bRequest response from the model (mistralai-mistral-medium-3.5-128b)mistralai / mistral-small-4-119b-2603Request response from the model (mistralai-mistral-small-4-119b-2603) moonshotai ModelEndpointmoonshotai-kimi-k2.6Request response from the model (kimi-k2.6) nvidia ModelEndpointnvidia / bevformerPost V1 Bevformer Process (bevformer)nvidia / cosmos-predict1-7b-nvidia / ising-calibration-1-35b-a3bRequest response from the model (ising-calibration-1-35b-a3b)nvidia / nemoretriever-parseRequest response from the model (nemoretriever-parse)nvidia / nemotron-3-nano-omni-30b-a3b-reasoningRequest response from the model (nvidia-nemotron-3-nano-omni-30b-a3b-reasoning)nvidia / nemotron-nano-12b-v2-vlRequest response from the model (nemotron-nano-12b-v2-vl)nvidia / nemotron-parseRequest response from the model (nemotron-parse)nvidia / nv-dinov2Run inference on the input image (nv-dinov2)nvidia / nv-grounding-dinoRun inference on the input image/video for a given text prompt (nv-grounding-dino)nvidia / retail-object-detectionRequest response from the model (retail-object-detection)nvidia / sparsedrivePost V1 Sparsedrive Inference (sparsedrive)nvidia / streampetrPost V1 Streampetr Process (streampetr)nvidia / vilaRequest response from the model (vila)nvidia / visual-changenetRequest response from the model (visual-changenet) stabilityai ModelEndpointstabilityai / stable-diffusion-3-mediumRequest generation (stable-diffusion-3-medium)stabilityai / stable-diffusion-xlRequest generation (stable-diffusion-xl)stabilityai / stable-video-diffusionRequest generation (stable-video-diffusion)Updated 4 days ago
