nvidia/Nemotron-3-Embed-8B

deepinfra/nvidia/Nemotron-3-Embed-8B

NVIDIA's larger Nemotron 3 text embedding model (July 2026), built on Ministral 3 8B with bidirectional attention: 4096-dimension vectors that can be truncated, 32K-token inputs, and strong multilingual and cross-lingual retrieval for RAG.

Get API Key Read the Docs

curl "$AUDIOLAB_API_URL/v1/embeddings" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/nvidia/Nemotron-3-Embed-8B",
  "input": "Build search with AudioLab.",
  "encoding_format": "float"
}'

Input Price: $0.0298 / 1M tokens
Output Price: —
Context: 32.8K tokens
Output: Embedding

Capabilities

Explore what nvidia/Nemotron-3-Embed-8B supports, then use the API section for a request tailored to this model.

Batch

Model Information

Provider: DeepInfra
Product: Embeddings
Release Date: Jul 16, 2026
Data Policy: Not specified
Region: US
Input: Text
Output: Embedding

Provider Documentation

Playground

Try nvidia/Nemotron-3-Embed-8B by DeepInfra. Requests use the selected workspace’s credits and API pricing.

nvidia/Nemotron-3-Embed-8B

This model uses a dedicated input format. Explore its API example or open the supported playground.

View API reference

Providers

Compare available endpoints, pricing, and context limits for nvidia/Nemotron-3-Embed-8B.

Provider	Context	Output	Input Price	Output Price	Endpoint
DeepInfra	32.8K tokens	Embedding	$0.0298 / 1M tokens	—	`nvidia/Nemotron-3-Embed-8B`

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Dimensions	4096
Max batch	8
Max total tokens	262144

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

A live availability check is not available right now.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

curl "$AUDIOLAB_API_URL/v1/embeddings" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/nvidia/Nemotron-3-Embed-8B",
  "input": "Build search with AudioLab.",
  "encoding_format": "float"
}'

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`deepinfra/nvidia/Nemotron-3-Embed-8B` — Required model identifier.
`input`	View Accepted Values
`encoding_format`	View Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Dimensions	4096
Max batch	8
Max total tokens	262144

Similar Models

Explore more embeddings and compare their capabilities.

Model	Context	Input Price	Output Price
nvidia/Nemotron-3-Embed-1B-BF16DeepInfra	32.8K tokens	$0.0128 / 1M tokens	—
nvidia/Nemotron-3-Embed-1B-NVFP4DeepInfra	32.8K tokens	$0.0085 / 1M tokens	—
nvidia/llama-nemotron-embed-vl-1b-v2DeepInfra	10.2K tokens	$0.0085 / 1M tokens	—
google/embeddinggemma-300mDeepInfra	2K tokens	$0.0017 / 1M tokens	—
Qwen/Qwen3-Embedding-0.6BDeepInfra	32.8K tokens	$0.0085 / 1M tokens	—
Qwen/Qwen3-Embedding-4BDeepInfra	32.8K tokens	$0.017 / 1M tokens	—

View All Embeddings