{"data":{"id":"deepinfra/nvidia/llama-nemotron-embed-vl-1b-v2","provider_id":"deepinfra","name":"nvidia/llama-nemotron-embed-vl-1b-v2","modalities":["text"],"context_window":10240,"family":"llama-nemotron-embed-vl-1b-v2","status":"active","description":"The llama-nemotron-embed-vl-1b-v2 is a high-performance multimodal embedding model designed to transform text queries and document images into dense vector representations for advanced retrieval systems. It excels at understanding complex visual content like charts, tables, and infographics.","architecture":null,"supported_parameters":["embed"],"created_at":null,"canonical_slug":"nvidia/llama-nemotron-embed-vl-1b-v2","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.01,"savings_pct":null,"savings_basis":null,"provider":{"id":"deepinfra","name":"DeepInfra","website":"https://deepinfra.com","categories":["text","image","audio","video"],"docs_url":"https://deepinfra.com/pricing","notes":"Secondary live feed from DeepInfra's public models API. Prices are DeepInfra's rates, not the origin lab's. Does not block the OpenRouter sync.","role":"host"},"prices":[{"id":60364,"model_id":"deepinfra/nvidia/llama-nemotron-embed-vl-1b-v2","unit":"token","input_per_1m_usd":0.01,"output_per_1m_usd":null,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/nvidia/llama-nemotron-embed-vl-1b-v2","notes":"DeepInfra public models API. Token and character rates are already USD per 1M. Per-image and per-second rates are stored as flat USD. Discount, when present, is not applied.","last_verified_at":"2026-10-08T17:11:32.756Z","source":"deepinfra","confidence":"official","cache_read_per_1m_usd":null,"cache_write_per_1m_usd":null,"cache_write_1h_per_1m_usd":null,"pricing_detail":null,"long_context_override":false}]}}