{"model_name":"nvidia/llama-nemotron-embed-vl-1b-v2","type":"embeddings","tags":["openai","priority"],"reported_type":"embeddings","version":"BB10mJOc","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.","mf_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.","featured":false,"owner":false,"public":true,"curl_inv":"curl -X POST \\\n    -d '{\"inputs\": [\"I like chocolate\"]}'  \\\n    -H \"Authorization: bearer $DEEPINFRA_API_KEY\"  \\\n    -H 'Content-Type: application/json'  \\\n    'https://api.deepinfra.com/v1/inference/nvidia/llama-nemotron-embed-vl-1b-v2'","cmdline_inv":"","txt_docs":"parameters:\n  service_tier: string. The service tier used for processing the request. 'priority' processes the request with higher priority (premium rate); 'flex' processes it at lower priority for a discount, served only when spare capacity exists and may be retried/timed out under load. Both apply only to models that support the respective tier. For compatibility, 'auto' is treated as 'priority' and 'standard_only' as 'default'.\n  fail_fast : (Default: False) boolean. If true, the request is rejected immediately with HTTP 429 when the model has no spare capacity, instead of waiting in the queue. Opt-in; the default (false) keeps standard queueing behavior.\n  inputs    : (Default: []) array. sequences to embed\n  normalize : (Default: False) boolean. whether to normalize the computed embeddings\n  image     : binary. image to embed. image file bytes in supported format (jpg, png)\n  dimensions: integer. The number of dimensions in the embedding. If not provided, the model's default will be used.If provided bigger than model's default, the embedding will be padded with zeros.\n  custom_instruction: string. Custom instruction prepending to each input. If empty, no instruction will be used.\n  multimodal_inputs: array. None\n  webhook   : string. The webhook to call when inference is done, by default you will get the output in the response of your inference request\n\nsend the parameters as EITHER:\n- JSON object (one key: value per parameter, binary as base64 or Data URL)\n- HTTP multipart (one part per parameter).\n","out_example":"{\n  \"embeddings\": [\n    [\n      0.0,\n      0.5,\n      1.0\n    ],\n    [\n      1.0,\n      0.5,\n      0.0\n    ]\n  ],\n  \"input_tokens\": 42,\n  \"embedding_jsons\": [\n    \"[0.0, 0.5, 1.0]\",\n    \"[1.0, 0.5, 0.0]\"\n  ],\n  \"request_id\": null,\n  \"inference_status\": {\n    \"status\": \"unknown\",\n    \"runtime_ms\": 0,\n    \"cost\": 0.0,\n    \"tokens_generated\": 0,\n    \"tokens_input\": 0,\n    \"output_length\": 0\n  }\n}\n","out_docs":"embeddings: array[array]. the computed embeddings for each input sequence or a single embedding if an image was passed\ninput_tokens: integer. The number of input tokens in the request\nembedding_jsons: array[string]. json representation of embeddings\nrequest_id: string. The request id\ninference_status: object. Object containing the status of the inference request\n","in_schema":{"definitions":{"ServiceTier":{"enum":["default","priority","flex"],"title":"ServiceTier","type":"string"}},"title":"EmbeddingsIn","type":"object","properties":{"service_tier":{"$ref":"#/definitions/ServiceTier","description":"The service tier used for processing the request. 'priority' processes the request with higher priority (premium rate); 'flex' processes it at lower priority for a discount, served only when spare capacity exists and may be retried/timed out under load. Both apply only to models that support the respective tier. For compatibility, 'auto' is treated as 'priority' and 'standard_only' as 'default'.","type":"string","title":"ServiceTier"},"fail_fast":{"default":false,"description":"If true, the request is rejected immediately with HTTP 429 when the model has no spare capacity, instead of waiting in the queue. Opt-in; the default (false) keeps standard queueing behavior.","title":"Fail Fast","type":"boolean"},"inputs":{"default":[],"description":"sequences to embed","items":{"type":"string"},"maxItems":1024,"soft_required":true,"title":"Inputs","type":"array","example":["I like chocolate"]},"normalize":{"default":false,"description":"whether to normalize the computed embeddings","title":"Normalize","type":"boolean","example":true},"image":{"description":"image to embed","format":"binary","is_image":true,"title":"Image","type":"string"},"dimensions":{"description":"The number of dimensions in the embedding. If not provided, the model's default will be used.If provided bigger than model's default, the embedding will be padded with zeros.","maximum":8192,"minimum":32,"title":"Dimensions","type":"integer","example":1536},"custom_instruction":{"description":"Custom instruction prepending to each input. If empty, no instruction will be used.","maxLength":512,"title":"Custom Instruction","type":"string","example":"Given a web search query, retrieve relevant passages that answer the query"},"multimodal_inputs":{"items":{"additionalProperties":true,"type":"object"},"title":"Multimodal Inputs","type":"array"},"webhook":{"description":"The webhook to call when inference is done, by default you will get the output in the response of your inference request","format":"uri","is_base_field":true,"maxLength":2083,"minLength":1,"title":"Webhook","type":"string"}}},"out_schema":{"definitions":{"InferenceReplyStatus":{"properties":{"status":{"choices":["unknown","queued","running","succeeded","failed"],"default":"succeeded","description":"Inference status","title":"Status","type":"string"},"runtime_ms":{"default":0,"description":"runtime in milliseconds","title":"Runtime Ms","type":"integer"},"cost":{"description":"estimated cost billed for the request in USD","title":"Cost","type":"number"},"tokens_generated":{"description":"number of tokens generated","title":"Tokens Generated","type":"integer"},"tokens_input":{"description":"number of input tokens","title":"Tokens Input","type":"integer"},"output_length":{"description":"length of the output in seconds","title":"Output Length","type":"integer"}},"required":["cost"],"title":"InferenceReplyStatus","type":"object"}},"exclude":["embedding_jsons"],"required":["embeddings","input_tokens"],"title":"EmbeddingsOut","type":"object","properties":{"embeddings":{"description":"the computed embeddings for each input sequence or a single embedding if an image was passed","items":{"items":{"type":"number"},"type":"array"},"title":"Embeddings","type":"array","example":[[0,0.5,1],[1,0.5,0]]},"input_tokens":{"description":"The number of input tokens in the request","title":"Input Tokens","type":"integer","example":42},"embedding_jsons":{"description":"json representation of embeddings","items":{"type":"string"},"title":"Embedding Jsons","type":"array","example":["[0.0, 0.5, 1.0]","[1.0, 0.5, 0.0]"]},"request_id":{"description":"The request id","is_base_field":true,"title":"Request Id","type":"string"},"inference_status":{"$ref":"#/definitions/InferenceReplyStatus","description":"Object containing the status of the inference request","is_base_field":true,"type":"object","title":"InferenceReplyStatus"}}},"in_fields":[{"name":"service_tier","parent":null,"ftype":"string","description":"The service tier used for processing the request. 'priority' processes the request with higher priority (premium rate); 'flex' processes it at lower priority for a discount, served only when spare capacity exists and may be retried/timed out under load. Both apply only to models that support the respective tier. For compatibility, 'auto' is treated as 'priority' and 'standard_only' as 'default'.","allowed":["default","priority","flex"],"default":null,"examples":[],"minimum":null,"exclusiveMinimum":null,"maximum":null,"exclusiveMaximum":null},{"name":"fail_fast","parent":null,"ftype":"boolean","description":"If true, the request is rejected immediately with HTTP 429 when the model has no spare capacity, instead of waiting in the queue. Opt-in; the default (false) keeps standard queueing behavior.","allowed":null,"default":false,"examples":[],"minimum":null,"exclusiveMinimum":null,"maximum":null,"exclusiveMaximum":null},{"name":"inputs","parent":null,"ftype":"array","description":"sequences to embed","allowed":null,"default":[],"examples":[["I like chocolate"]],"minimum":null,"exclusiveMinimum":null,"maximum":null,"exclusiveMaximum":null},{"name":"normalize","parent":null,"ftype":"boolean","description":"whether to normalize the computed embeddings","allowed":null,"default":false,"examples":[true],"minimum":null,"exclusiveMinimum":null,"maximum":null,"exclusiveMaximum":null},{"name":"image","parent":null,"ftype":"string","description":"image to embed","allowed":null,"default":null,"examples":[],"minimum":null,"exclusiveMinimum":null,"maximum":null,"exclusiveMaximum":null},{"name":"dimensions","parent":null,"ftype":"integer","description":"The number of dimensions in the embedding. If not provided, the model's default will be used.If provided bigger than model's default, the embedding will be padded with zeros.","allowed":null,"default":null,"examples":[1536],"minimum":32.0,"exclusiveMinimum":null,"maximum":8192.0,"exclusiveMaximum":null},{"name":"custom_instruction","parent":null,"ftype":"string","description":"Custom instruction prepending to each input. If empty, no instruction will be used.","allowed":null,"default":null,"examples":["Given a web search query, retrieve relevant passages that answer the query"],"minimum":null,"exclusiveMinimum":null,"maximum":null,"exclusiveMaximum":null},{"name":"multimodal_inputs","parent":null,"ftype":"array","description":null,"allowed":null,"default":null,"examples":[],"minimum":null,"exclusiveMinimum":null,"maximum":null,"exclusiveMaximum":null},{"name":"webhook","parent":null,"ftype":"file","description":"The webhook to call when inference is done, by default you will get the output in the response of your inference request","allowed":null,"default":null,"examples":[],"minimum":null,"exclusiveMinimum":null,"maximum":null,"exclusiveMaximum":null}],"pricing":{"discount":null,"discount_ends_at":null,"short":null,"full":null,"table":null,"type":"input_tokens","cents_per_input_token":1e-06,"cents_per_image_token":null},"doc_blocks":[{"key":"openai-emb-http","url":"/models/nvidia/llama-nemotron-embed-vl-1b-v2/docs/openai-emb-http.md"},{"key":"openai-emb-py","url":"/models/nvidia/llama-nemotron-embed-vl-1b-v2/docs/openai-emb-py.md"},{"key":"openai-emb-js","url":"/models/nvidia/llama-nemotron-embed-vl-1b-v2/docs/openai-emb-js.md"},{"key":"http","url":"/models/nvidia/llama-nemotron-embed-vl-1b-v2/docs/http.md"},{"key":"js-emb","url":"/models/nvidia/llama-nemotron-embed-vl-1b-v2/docs/js-emb.md"}],"short_doc_block":null,"schemas":[{"key":"openai-embeddings","url":"/models/nvidia/llama-nemotron-embed-vl-1b-v2/schema/openai-embeddings"},{"key":"default","url":"/models/nvidia/llama-nemotron-embed-vl-1b-v2/schema/default"}],"meta":{"paper_url":"https://huggingface.co/nvidia/llama-nemotron-embed-vl-1b-v2","license_url":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/","readme":"https://shared.deepinfra.com/models/nvidia/llama-nemotron-embed-vl-1b-v2/readme.6c1de8bed2d6c368a7031e2ca75bd47d78472598dc975ebd842d538beb5dc39e.md","cover_img_url":"https://shared.deepinfra.com/models/nvidia/llama-nemotron-embed-vl-1b-v2/cover_image.0deeac95c09a3337a78eec5581adfcc84991a787274d6695760f738688733ad5.webp"},"max_tokens":10240,"max_output_tokens":null,"replaced_by":null,"deprecated":null,"quantization":null,"mmlu":null,"expected":null,"import_time":"2026-03-11T14:45:29.834454+00:00","is_partner":false,"is_custom_deployable":false,"mf_name":"nemotron","mf_title":"Nemotron"}