Marketplace · Embeddings

nomic-embed-text:latest

Call nomic-embed-text:latest through one OpenAI-compatible API. It's served by 2 hosts on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.004
per 1M tokens
£1 buys about 250 million tokens (≈ 190 million words)
Hosts
2
Loaded now
1

At a glance.

  • Type: Embeddings
  • Hosts serving it now: 2 (1 with it loaded in memory)
  • Engines: ollama
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
vec = client.embeddings.create(
    model="nomic-embed-text:latest",
    input="text to embed",
)

nomic-embed-text:latest in detail.

A high-performing open embedding model with a large token context window.

Published by
nomic-ai
Parameters
137M
Download size
274 MB (as packaged for Ollama)
Quantisation
F16
Format
gguf
Architecture
nomic_bert
Licence
Apache 2.0
Task
sentence similarity
Library
sentence-transformers
Languages
en
First published
10 Feb 2024
Last updated
7 Apr 2026
Downloads (30 days)
11.9 million on Hugging Face
Likes
988

sentence-transformers onnx nomic_bert feature-extraction sentence-similarity mteb transformers.js en text-embeddings-inference

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

nomic-embed-text-v1.5: Resizable Production Embeddings with Matryoshka Representation Learning

Blog | Technical Report | AWS SageMaker | Nomic Platform

Exciting Update!: nomic-embed-text-v1.5 is now multimodal! nomic-embed-vision-v1.5 is aligned to the embedding space of nomic-embed-text-v1.5, meaning any text embedding is multimodal!

Usage

Important: the text prompt must include a task instruction prefix, instructing the model which task is being performed.

For example, if you are implementing a RAG application, you embed your documents as search_document: and embed your user queries as search_query: .

Notice: From transformers v5.5.0 and sentence transformers v5.3.0, trust_remote_code=True will no longer be necessary. This will only be possible with the text-only series as of now.

Task instruction prefixes

search_document

Purpose: embed texts as documents from a dataset

This prefix is used for embedding texts as documents, for example as documents for a RAG index.

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5")
sentences = ['search_document: TSNE is a dimensionality reduction algorithm created by Laurens van Der Maaten']
embeddings = model.encode(sentences)
print(embeddings)

search_query

Purpose: embed texts as questions to answer

This prefix is used for embedding texts as questions that documents from a dataset could resolve, for example as queries to be answered by a RAG application.

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5")
sentences = ['search_query: Who is Laurens van Der Maaten?']
embeddings = model.encode(sentences)
print(embeddings)

clustering

Purpose: embed texts to group them into clusters

This prefix is used for embedding texts in order to group them into clusters, discover common topics, or remove semantic duplicates.

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5")
sentences = ['clustering: the quick brown fox']
embeddings = model.encode(sentences)
print(embeddings)

classification

Purpose: embed texts to classify them

This prefix is used for embedding texts into vectors that will be used as features for a classification model

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5")
sentences = ['classification: the quick brown fox']
embeddings = model.encode(sentences)
print(embeddings)

Sentence Transformers

import torch.nn.functional as F
from sentence_transformers import SentenceTransformer

matryoshka_dim = 512

model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5")
sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']
embeddings = model.encode(sentences, convert_to_tensor=True)
embeddings = F.layer_norm(embeddings, normalized_shape=(embeddings.shape[1],))
embeddings = embeddings[:, :matryoshka_dim]
embeddings = F.normalize(embeddings, p=2, dim=1)
print(embeddings)

Transformers

import torch
import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModel

def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0]
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']

tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1.5')
model.eval()

encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

+ matryoshka_dim = 512

with torch.no_grad():
    model_output = model(**encoded_input)

embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+ embeddings = F.layer_norm(embeddings, normalized_shape=(embeddings.shape[1],))
+ embeddings = embeddings[:, :matryoshka_dim]
embeddings = F.normalize(embeddings, p=2, dim=1)
print(embeddings)

The model natively supports scaling of the sequence length past 2048 tokens. To do so,

- tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
+ tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192)

- model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1.5')
+ rope_parameters = {"rope_theta": 1000.0, "rope_type": "dynamic", "factor": 2.0}
+ model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1.5', rope_parameters=rope_parameters)
Read the rest of the model card

Transformers.js

import { pipeline, layer_norm } from '@huggingface/transformers';

// Create a feature extraction pipeline
const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1.5');

// Define sentences
const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'];

// Compute sentence embeddings
let embeddings = await extractor(texts, { pooling: 'mean' });
console.log(embeddings); // Tensor of shape [2, 768]

const matryoshka_dim = 512;
embeddings = layer_norm(embeddings, [embeddings.dims[1]])
    .slice(null, [0, matryoshka_dim])
    .normalize(2, -1);
console.log(embeddings.tolist());

Nomic API

The easiest way to use Nomic Embed is through the Nomic Embedding API.

Generating embeddings with the nomic Python client is as easy as

from nomic import embed

output = embed.text(
    texts=['Nomic Embedding API', '#keepAIOpen'],
    model='nomic-embed-text-v1.5',
    task_type='search_document',
    dimensionality=256,
)

print(output)

For more information, see the API reference

Infinity

Usage with Infinity.

docker run --gpus all -v $PWD/data:/app/.cache -e HF_TOKEN=$HF_TOKEN -p "7997":"7997" \
michaelf34/infinity:0.0.70 \
v2 --model-id nomic-ai/nomic-embed-text-v1.5 --revision "main" --dtype float16 --batch-size 8 --engine torch --port 7997 --no-bettertransformer

Adjusting Dimensionality

nomic-embed-text-v1.5 is an improvement upon Nomic Embed that utilizes Matryoshka Representation Learning which gives developers the flexibility to trade off the embedding size for a negligible reduction in performance.

NameSeqLenDimensionMTEB
nomic-embed-text-v1819276862.39
nomic-embed-text-v1.5819276862.28
nomic-embed-text-v1.5819251261.96
nomic-embed-text-v1.5819225661.04
nomic-embed-text-v1.5819212859.34
nomic-embed-text-v1.581926456.10

Training

Click the Nomic Atlas map below to visualize a 5M sample of our contrastive pretraining data!

We train our embedder using a multi-stage training pipeline. Starting from a long-context BERT model, the first unsupervised contrastive stage trains on a dataset generated from weakly related text pairs, such as question-answer pairs from forums like StackExchange and Quora, title-body pairs from Amazon reviews, and summarizations from news articles.

In the second finetuning stage, higher quality labeled datasets such as search queries and answers from web searches are leveraged. Data curation and hard-example mining is crucial in this stage.

For more details, see the Nomic Embed Technical Report and corresponding blog post.

Training data to train the models is released in its entirety. For more details, see the contrastors repository

Join the Nomic Community

Citation

If you find the model, dataset, or training code useful, please cite our work

@misc{nussbaum2024nomic,
      title={Nomic Embed: Training a Reproducible Long Context Text Embedder}, 
      author={Zach Nussbaum and John X. Morris and Brandon Duderstadt and Andriy Mulyar},
      year={2024},
      eprint={2402.01613},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Sources: nomic-ai/nomic-embed-text-v1.5 on Hugging Face · nomic-embed-text:latest on Ollama. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving nomic-embed-text:latest right now
HostTierPriceMeasured speedHealthStateRent
Lumaram-MacMini-M4-001L1£0.00432 ms81loads on request—
Apple M4 (16 GIG )L1£0.033068 ms84loaded—

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

2 machines serve nomic-embed-text:latest today. Every extra host is somewhere a request can fail over to when one drops, and spare capacity when demand spikes. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
2
1 loaded in memory
Price to beat
£0.004
per 1M tokens
Fastest measured
32 ms

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load nomic-embed-text:latest, and the platform benchmarks it on your hardware before your first request.