Nemotron 3 Ultra 550B A55B
nvidia-nemotron-3-ultra-550bFrontier-scale open reasoning model for complex agents and long-context code.
Nemotron and Cosmos models for open reasoning, coding, voice and physical AI video.
nvidia-nemotron-3-ultra-550bFrontier-scale open reasoning model for complex agents and long-context code.
nvidia-nemotron-3-super-120bEfficient open MoE for reasoning, planning, coding and tool calling.
nvidia-nemotron-3-nano-omniOmnimodal model that understands video, speech, images and text.
nvidia-nemotron-voicechatFull-duplex speech-to-speech model that listens and speaks simultaneously.
nvidia-nemotron-asr-streamingLow-latency streaming speech recognition for enterprise voice systems.
nvidia-magpie-tts-zeroshotExpressive zero-shot text-to-speech from a short voice sample.
nvidia-cosmos3-nanoPhysics-aware video world generation from text or image prompts.
nvidia-cosmos3-nano-reasonerStructured physical-world reasoning over video and image inputs.
nvidia-nemotron-ocr-v1Fast OCR with layout, table and document structure extraction.
Pricing is shown in USD per one million tokens. Route availability and preview pricing can vary by region and account.