NVIDIA: Llama Nemotron Embed VL 1B V2 (free)
Llama Nemotron Embed VL 1B V2 is NVIDIA’s multimodal embedding model for retrieval. It turns text, images or combined document inputs into vectors and supports text-query search over documents containing tables, charts, text and infographics.
About the model
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Llama Nemotron Embed VL 1B V2 is NVIDIA’s embedding model for multimodal question-answering retrieval. It can represent a document as text, an image or a combination of image and text. A text query can then be used to retrieve related documents. Its published profile supports document images containing text, tables, charts and infographics, and returns embedding vectors.
Prepare identifiable document items
Keep each input connected to the source document, page or passage it represents. For a visual page, preserve the image and any accompanying text that belongs to it. For a text passage, retain its title or section label when that helps interpret a later match. These source identifiers make a retrieved item useful as evidence rather than only as a numeric similarity result.
Choose item boundaries around the material a user needs to find. A chart and its explanation may belong together; unrelated pages should retain their separate identities. Review whether the input is readable and whether the text or image contains the information the intended query is meant to retrieve.
Text queries and vector retrieval
The model’s role is to produce vectors for retrieval, with text as the query form described by the profile. Keep the query and indexed items in a compatible embedding setup. The application stores the vectors, compares them and returns the corresponding source items. The retrieved document remains the material to inspect or pass to a later answer-generation step.
A useful test set includes the questions users actually ask and the pages that should be found. Review wrong or missing matches against the source content and item boundaries. Retain the full document identifier with any selected passage or image so the result can be checked in context.
Input allowance and the search artifact
The documented hosted profile lists up to 131,072 tokens per input. Split larger source sets into separate, labeled inputs and preserve their relationships. The profile’s vector output is not a generated prose answer or a transcript; a later application stage can use the retrieved evidence to answer a question.
A completed retrieval artifact joins the query, selected source items and their identifiers. Preserve the embedding model and input preparation used for an index, so later changes can be distinguished from changes in the source collection.
Ailoot Ultra · Embeddings POST /v1/embeddings nvidia/llama-nemotron-embed-vl-1b-v2:free
nvidia/llama-nemotron-embed-vl-1b-v2:free
nvidia/llama-nemotron-embed-vl-1b-v2:freeOverview
Llama Nemotron Embed VL 1B V2 is NVIDIA’s multimodal embedding model for retrieval. It turns text, images or combined document inputs into vectors and supports text-query search over documents containing tables, charts, text and infographics.
- Accepted inputs
- Text · token_ids
- Results
- embedding
Available in Ailoot · inputs & methods
Ailoot Ultra · Embeddings POST /v1/embeddings
- Input types
text,token_ids- Output types
embedding- Context
- 131,072 tokens
- Output format
- json
| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits nvidia/llama-nemotron-embed-vl-1b-v2:free | Default— |
Fieldinput | Typestring|string[]|integer[]|integer[][] | RequirementRequired | Values & limits Minimum items: 1 Conditions: Nonempty homogeneous batch. Token IDs are nonnegative integers. Input budget: Maximum: 131,072 · Text unit: UTF8 bytes · Token unit: token-array elements | Default— |
Fieldencoding_format | Typestring | RequirementOptional | Values & limits float | Defaultfloat |
Fielddimensions | Typeinteger | RequirementNot supported | Values & limits Minimum: 1 | Default— |
Fielduser | Typejson_value | RequirementOptional | Values & limits Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific. | Default— |
Fieldsession_id | Typejson_value | RequirementOptional | Values & limits Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific. | Default— |
Fieldtrace | Typejson_value | RequirementOptional | Values & limits Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific. | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options rejected | Default— |
Input material combinations
text_to_embedding
Method parameters and lifecycle
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, input |
Parameterinput_shapes | Contractstring, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[] |
Parameterencoding_format | Contractfloat |
Parameterdimensions_override | Contractfalse |
Parametermax_input_budget_units | Contract131072 |
Parametermultimodal_objects | Contractfalse |
Parametermaterial_types | Contracttext, token_ids |
Lifecycle: synchronous_json
Keep every vector index and dimension.
Multimodal model name does not admit image objects on this exact path.
Pricing
Tariff references do not add request options. Supported parameters are listed for the selected method.
- Fast mode
- Standard rate When fast mode is selected
- Flex mode
- Standard rate When flex mode is selected
- Maximum reasoning effort
- Standard rate When maximum reasoning effort uses the default adjustment
Ailoot rates
Prices by configuration
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Example requests
Ailoot Ultra · Embeddings
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "nvidia/llama-nemotron-embed-vl-1b-v2:free", "input": ["First document", "Second document"]}')
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("data",[]): print(json.dumps({"index":x.get("index"),"embedding":x.get("embedding")}))
PY_RESULT
from openai import OpenAI
import os
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.embeddings.create(model='nvidia/llama-nemotron-embed-vl-1b-v2:free',input=["First document","Second document"])
print(result)
for item in result.data:print(item.index,item.embedding)
Receive and save results
Ailoot Ultra · Embeddings
json
Keep all completed results
Keep every complete returned response, file and content part.
Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.
If the original response needs checking
No embedding job endpoint is introduced.
Response fields
| Field | Type |
|---|---|
Fieldobject | Typestring |
Fieldmodel | Typestring |
Fielddata[].index | Typeinteger |
Fielddata[].embedding | Typefinite float[] |
Fieldusage | Typeobject |
Errors and next steps
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Aliases
Model aliases
Ailoot Ultra nvidia/llama-nemotron-embed-vl-1b-v2:free
Method path aliases
Use the method paths shown above.
Related caller IDs
FAQ · NVIDIA: Llama Nemotron Embed VL 1B V2 (free)
- What inputs and results are available?
POST /v1/embeddings·nvidia/llama-nemotron-embed-vl-1b-v2:free:text,token_ids→embedding- Which fields does the request use?
POST /v1/embeddings·nvidia/llama-nemotron-embed-vl-1b-v2:free:model,input,encoding_format,provider- What limits apply?
POST /v1/embeddings·nvidia/llama-nemotron-embed-vl-1b-v2:free:ctx:131072;input.budget.maximum:131072(UTF8 bytes);input.min_items:1