Source: https://ailoot.ai/models/en/nvidia-nemotron-3-embed-1b/
Canonical: https://ailoot.ai/models/en/nvidia-nemotron-3-embed-1b/
Language: en

# Nemotron 3 Embed 1B

[Markdown](https://ailoot.ai/models/en/nvidia-nemotron-3-embed-1b/index.md) · [JSON](https://ailoot.ai/models/en/nvidia-nemotron-3-embed-1b/facts.json)

## [Nemotron 3 Embed 1B](https://ailoot.ai/models/en/nvidia-nemotron-3-embed-1b/)

Nemotron 3 Embed 1B turns text into vectors for multilingual retrieval, code search and RAG. Processes sequences of up to 32,768 tokens and returns a 2048-dimensional representation.

- [**Ailoot · Embeddings** `POST /v1/embeddings` `nvidia/nemotron-3-embed-1b`](https://ailoot.ai/models/en/nvidia-nemotron-3-embed-1b/#method-0)
- [**Ailoot · Embeddings** `POST /v1/embeddings` `nemotron-3-embed`](https://ailoot.ai/models/en/nvidia-nemotron-3-embed-1b/#method-1)
- [**Ailoot · Embeddings** `POST /v1/embeddings` `nemotron-3-embed-latest`](https://ailoot.ai/models/en/nvidia-nemotron-3-embed-1b/#method-2)

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

Nemotron 3 Embed 1B is an NVIDIA text model for semantic retrieval and passage matching. It encodes questions, documents and program code into dense numerical vectors. These representations are used to find relevant context in large collections, add it to an assistant's response or retrieve previously saved information for an agent's next step.

#### Multilingual knowledge and code

The model is intended for multilingual and cross-language retrieval: a question and relevant material can be written in different languages. Russian belongs to the published set of 34 languages, alongside English, Ukrainian, Chinese, Japanese, Arabic and others. This is useful for shared knowledge bases where technical documents and user requests have not been standardized to one language.

Tasks include documentation search, text matching and code retrieval from a verbal description. A large input window allows work with long documents, extensive program context and the history of several agent steps. Retrieved material returns to the subsequent workflow as context; the next system component produces final explanations and answers.

#### From text to a vector

Input consists of text strings. Each string yields one vector of 2048 numbers. Maximum sequence length is 32,768 tokens; longer material needs to be divided into parts or shortened. Input preparation distinguishes a question from a document: the model was trained to match their roles, so the same string in these two tasks should not be formatted without accounting for its purpose.

Vectors are normalized to unit length. With this representation, dot product and cosine similarity provide equivalent comparison methods. The first 1024 or 512 coordinates of the full vector can be retained, but normalization must be performed again after truncation. This is a result-processing property; dimensionality should be selected consistently for the collection and queries.

#### How the compact model is built

The encoder contains approximately 1.14 billion parameters. It is derived from a model based on Ministral 3 3B through two stages of structured pruning and distillation. Bidirectional attention considers the entire input, then token representations are averaged into a shared vector.

NVIDIA releases BF16 and NVFP4 variants. Their representation spaces are close, but switching variants requires checks on one's own documents. Neither numerical similarity nor context length guarantees that retrieval always selects the correct passage.

**Ailoot · Embeddings** `POST /v1/embeddings` `nvidia/nemotron-3-embed-1b`

[`nvidia/nemotron-3-embed-1b`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nvidia%2Fnemotron-3-embed-1b&fmt=embeddings)

NVIDIA /`nvidia/nemotron-3-embed-1b`

Model ID

- `nvidia/nemotron-3-embed-1b`
- `nemotron-3-embed`
- `nemotron-3-embed-latest`

### Overview

Nemotron 3 Embed 1B turns text into vectors for multilingual retrieval, code search and RAG. Processes sequences of up to 32,768 tokens and returns a 2048-dimensional representation.

Accepted inputs

Text

Results

embedding

### Available in Ailoot · inputs & methods

**Ailoot · Embeddings** `POST /v1/embeddings`

Input types

`text`

Output types

`embedding`

Context

4,096 tokens

Output format

json

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits nvidia/nemotron-3-embed-1b | Default— |
| Field`input` | Type`string\|string[]` | RequirementRequired | Values & limits Minimum items: 1 Conditions: Every string nonempty after trim; data URIs are rejected; accepted budget measures relevant UTF8 bytes. | Default— |
| Field`input_type` | Type`string` | RequirementOptional | Values & limits query, passage | Defaultquery |
| Field`encoding_format` | Type`string` | RequirementOptional | Values & limits float, base64 | Defaultfloat |
| Field`truncate` | Type`string` | RequirementOptional | Values & limits NONE, START, END | Default— |
| Field`dimensions` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 | Default— |
| Field`user` | Type`string` | RequirementOptional | Values & limits | Default— |

Input material combinations

**text\_to\_embedding**

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.0001 */ 1K*

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 →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot · Embeddings

Embedding example

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "nvidia/nemotron-3-embed-1b", "input": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]=[text]
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
```

### Receive and save results

#### Ailoot · Embeddings

json

##### Keep all completed results

Keep every complete returned response, file and content part.

Decode base64 vectors only when that format was requested; retain every vector and its original index.

##### If the original response needs checking

No embedding job endpoint is introduced.

Response fields

| Field | Type |
| --- | --- |
| Field`data[].index` | Typeinteger |
| Field`data[].embedding` | Typefinite float\[\]\|base64 float32 vector |
| Field`model` | Typestring |
| Field`usage` | 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** [`nvidia/nemotron-3-embed-1b`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nvidia%2Fnemotron-3-embed-1b&fmt=embeddings), [`nemotron-3-embed`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed&fmt=embeddings), [`nemotron-3-embed-latest`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed-latest&fmt=embeddings)

#### Method path aliases

Use the method paths shown above.

#### Related caller IDs

[`nvidia/nemotron-3-embed-1b`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nvidia%2Fnemotron-3-embed-1b&fmt=embeddings), [`nemotron-3-embed`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed&fmt=embeddings), [`nemotron-3-embed-latest`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed-latest&fmt=embeddings)

**Ailoot · Embeddings** `POST /v1/embeddings` `nemotron-3-embed`

[`nemotron-3-embed`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed&fmt=embeddings)

NVIDIA /`nemotron-3-embed`

Model ID

- `nvidia/nemotron-3-embed-1b`
- `nemotron-3-embed`
- `nemotron-3-embed-latest`

### Overview

Nemotron 3 Embed 1B turns text into vectors for multilingual retrieval, code search and RAG. Processes sequences of up to 32,768 tokens and returns a 2048-dimensional representation.

Accepted inputs

Text

Results

embedding

### Available in Ailoot · inputs & methods

**Ailoot · Embeddings** `POST /v1/embeddings`

Input types

`text`

Output types

`embedding`

Context

4,096 tokens

Output format

json

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits nemotron-3-embed | Default— |
| Field`input` | Type`string\|string[]` | RequirementRequired | Values & limits Minimum items: 1 Conditions: Every string nonempty after trim; data URIs are rejected; accepted budget measures relevant UTF8 bytes. | Default— |
| Field`input_type` | Type`string` | RequirementOptional | Values & limits query, passage | Defaultquery |
| Field`encoding_format` | Type`string` | RequirementOptional | Values & limits float, base64 | Defaultfloat |
| Field`truncate` | Type`string` | RequirementOptional | Values & limits NONE, START, END | Default— |
| Field`dimensions` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 | Default— |
| Field`user` | Type`string` | RequirementOptional | Values & limits | Default— |

Input material combinations

**text\_to\_embedding**

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.0001 */ 1K*

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 →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot · Embeddings

Embedding example

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "nemotron-3-embed", "input": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]=[text]
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
```

### Receive and save results

#### Ailoot · Embeddings

json

##### Keep all completed results

Keep every complete returned response, file and content part.

Decode base64 vectors only when that format was requested; retain every vector and its original index.

##### If the original response needs checking

No embedding job endpoint is introduced.

Response fields

| Field | Type |
| --- | --- |
| Field`data[].index` | Typeinteger |
| Field`data[].embedding` | Typefinite float\[\]\|base64 float32 vector |
| Field`model` | Typestring |
| Field`usage` | 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** [`nvidia/nemotron-3-embed-1b`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nvidia%2Fnemotron-3-embed-1b&fmt=embeddings), [`nemotron-3-embed`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed&fmt=embeddings), [`nemotron-3-embed-latest`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed-latest&fmt=embeddings)

#### Method path aliases

Use the method paths shown above.

#### Related caller IDs

[`nvidia/nemotron-3-embed-1b`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nvidia%2Fnemotron-3-embed-1b&fmt=embeddings), [`nemotron-3-embed`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed&fmt=embeddings), [`nemotron-3-embed-latest`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed-latest&fmt=embeddings)

**Ailoot · Embeddings** `POST /v1/embeddings` `nemotron-3-embed-latest`

[`nemotron-3-embed-latest`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed-latest&fmt=embeddings)

NVIDIA /`nemotron-3-embed-latest`

Model ID

- `nvidia/nemotron-3-embed-1b`
- `nemotron-3-embed`
- `nemotron-3-embed-latest`

### Overview

Nemotron 3 Embed 1B turns text into vectors for multilingual retrieval, code search and RAG. Processes sequences of up to 32,768 tokens and returns a 2048-dimensional representation.

Accepted inputs

Text

Results

embedding

### Available in Ailoot · inputs & methods

**Ailoot · Embeddings** `POST /v1/embeddings`

Input types

`text`

Output types

`embedding`

Context

4,096 tokens

Output format

json

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits nemotron-3-embed-latest | Default— |
| Field`input` | Type`string\|string[]` | RequirementRequired | Values & limits Minimum items: 1 Conditions: Every string nonempty after trim; data URIs are rejected; accepted budget measures relevant UTF8 bytes. | Default— |
| Field`input_type` | Type`string` | RequirementOptional | Values & limits query, passage | Defaultquery |
| Field`encoding_format` | Type`string` | RequirementOptional | Values & limits float, base64 | Defaultfloat |
| Field`truncate` | Type`string` | RequirementOptional | Values & limits NONE, START, END | Default— |
| Field`dimensions` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 | Default— |
| Field`user` | Type`string` | RequirementOptional | Values & limits | Default— |

Input material combinations

**text\_to\_embedding**

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.0001 */ 1K*

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 →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot · Embeddings

Embedding example

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "nemotron-3-embed-latest", "input": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]=[text]
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
```

### Receive and save results

#### Ailoot · Embeddings

json

##### Keep all completed results

Keep every complete returned response, file and content part.

Decode base64 vectors only when that format was requested; retain every vector and its original index.

##### If the original response needs checking

No embedding job endpoint is introduced.

Response fields

| Field | Type |
| --- | --- |
| Field`data[].index` | Typeinteger |
| Field`data[].embedding` | Typefinite float\[\]\|base64 float32 vector |
| Field`model` | Typestring |
| Field`usage` | 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** [`nvidia/nemotron-3-embed-1b`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nvidia%2Fnemotron-3-embed-1b&fmt=embeddings), [`nemotron-3-embed`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed&fmt=embeddings), [`nemotron-3-embed-latest`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed-latest&fmt=embeddings)

#### Method path aliases

Use the method paths shown above.

#### Related caller IDs

[`nvidia/nemotron-3-embed-1b`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nvidia%2Fnemotron-3-embed-1b&fmt=embeddings), [`nemotron-3-embed`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed&fmt=embeddings), [`nemotron-3-embed-latest`](https://ailoot.ai/models/en/#m=nvidia%2Fnemotron-3-embed-1b&route=Core&caller=nemotron-3-embed-latest&fmt=embeddings)

FAQ · nvidia/nemotron-3-embed-1b

What inputs and results are available?

`POST /v1/embeddings` · `nvidia/nemotron-3-embed-1b`: `text` → `embedding` `POST /v1/embeddings` · `nemotron-3-embed`: `text` → `embedding` `POST /v1/embeddings` · `nemotron-3-embed-latest`: `text` → `embedding`

Which fields does the request use?

`POST /v1/embeddings` · `nvidia/nemotron-3-embed-1b`: `model`, `input`, `input_type`, `encoding_format`, `truncate`, `dimensions`, `user` `POST /v1/embeddings` · `nemotron-3-embed`: `model`, `input`, `input_type`, `encoding_format`, `truncate`, `dimensions`, `user` `POST /v1/embeddings` · `nemotron-3-embed-latest`: `model`, `input`, `input_type`, `encoding_format`, `truncate`, `dimensions`, `user`

What limits apply?

`POST /v1/embeddings` · `nvidia/nemotron-3-embed-1b`: `ctx`: `4096`; `input.min_items`: `1`; `dimensions.minimum`: `1` `POST /v1/embeddings` · `nemotron-3-embed`: `ctx`: `4096`; `input.min_items`: `1`; `dimensions.minimum`: `1` `POST /v1/embeddings` · `nemotron-3-embed-latest`: `ctx`: `4096`; `input.min_items`: `1`; `dimensions.minimum`: `1`

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

## The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

## Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription

Choose a discounted plan for your regular requests.

Promo code: up to 50% off

Enter your code at checkout. The price updates to reflect the current promotion.

Spending in your history

The model, tokens and amount are recorded for each request.

[Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/)

## Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application

Add text, image, video and audio generation to paid features in your service.

Reseller licence

Send a description of your project and how you provide access. Request written terms for use and resale.

Documents on the website

The service offer, licence agreement and data processing policy are available before you connect.

[Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.