GET
/v1/schemas/nvidia/embeddings/nvidia%2Fnemotron-3.5-embed-1b
Accept:
kind inputactivity embeddingshash 1fe8bb86…extracted Oct 21, 2026version currentsource upstream spec ↗
Request body
10 properties · 2 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| input* | string | string[] | Input to embed. Each item is text, one image, or text followed by one image. Send an image as a base64 data URL, for example `data:image/png;base64,<data>`, or as an `<img src="data:image/png;base64,<data>">` tag. PNG and JPEG images are supported, with one im… | length ≥ 1 |
| model* | string | ID of the embedding model. | default: "nvidia/nemotron-3.5-embed-1b" |
| input_type | enum | nvidia/nemotron-3.5-embed-1b operates in `passage` or `query` mode, and thus requires the `input_type` parameter. `passage` is used when generating embeddings during indexing. `query` is used when generating embeddings during querying. Inputs that contain an i… | passage | query |
| modality | enum | The modality of each input item: `text`, `image`, or `text_image`. Give one value for all items, or one value per item. If omitted, the modality is inferred from the input. | text | image | text_image |
| encoding_format | enum | The format to return the embeddings in. | float | base64 · default: "float" |
| truncate | enum | Specifies how inputs longer than the maximum token length (10240) are handled. `END` discards the end of the text until the input fits. `NONE` returns an error when the input exceeds the maximum. `START` is not supported. The image and the passage prefix must … | NONE | END · default: "END" |
| dimensions | integer | Number of dimensions of the returned embedding, from 128 through the native dimension of 2048. Shortened vectors are L2-normalized again. Omit to receive the native 2048-dimensional embedding. | 128 ≤ n ≤ 2048 |
| embedding_type | enum | Output representation of each embedding value. Quantized representations pack several dimensions into each output element. | float | int8 | uint8 | binary | ubinary · default: "float" |
| longest_edge | integer | Maximum image size before patch-grid alignment. Larger images are downsized while preserving the aspect ratio; smaller images are not enlarged. Omit to use the model default of 1120. Use the same value when indexing and querying. | 256 ≤ n ≤ 1540 |
| user | string | Optional identifier for the end user. If provided it must be non-blank and at most 512 characters. It does not select the model or authorize the request. | length ≤ 512 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"nvidia","endpointId":"nvidia/nemotron-3.5-embed-1b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}