Nomic AI - Open weights - verified
Nomic Embed Text v2 MoE embeddings
Nomic Embed Text v2 MoE is a current embedding model from Nomic AI, with open weights on Hugging Face at nomic-ai/nomic-embed-text-v2-moe. It returns 768-dimension vectors by default and accepts up to 512 input tokens, for text input. There is no API price: the weights download from Hugging Face under Apache 2.0, and you pay for the compute you run them on.
CurrentModel id: nomic-ai/nomic-embed-text-v2-moe- weights: nomic-ai/nomic-embed-text-v2-moe
- Default dims
- 768
- Max input
- 512 tok
- Price / 1M
- Self-hosted
- Inputs
- Text
Dimensions
Flexible output size- 768default
- 256
Default output: 768 dimensions.
Listed sizes: 768 and 256.
Nomic AI documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.
Pricing
No API price: the weights are on Hugging Face and you run them on your own hardware or host.
Open weights
- Hugging Face repo
- nomic-ai/nomic-embed-text-v2-moe
- License
- Apache 2.0
apache-2.0 - Commercial use
- Commercial use allowedCommercial use is allowed, per the license.
- Parameters
- 475M (475,292,928)
Worth knowing
Mixture of Experts model (8 experts, top-2 routing, 305M of 475M parameters active) that requires the `search_query: ` and `search_document: ` prefixes and trust_remote_code=True.
Released . Multilingual: yes.
Usage
Copied verbatim from the page linked below. Placeholders such as project ids and API keys are the source's own.
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("nomic-ai/nomic-embed-text-v2-moe", trust_remote_code=True)
sentences = ["Hello!", "¡Hola!"]
embeddings = model.encode(sentences, prompt_name="passage")
print(embeddings.shape)
# (2, 768)
similarity = model.similarity(embeddings[0], embeddings[1])
print(similarity)
# tensor([[0.9118]])FAQ
How many dimensions does Nomic Embed Text v2 MoE output?
Default output: 768 dimensions. Listed sizes: 768 and 256. Nomic AI documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.
What is the max input length of Nomic Embed Text v2 MoE?
512 tokens per input, per the model card. Longer text has to be chunked before you embed it.
Can I use Nomic Embed Text v2 MoE commercially?
Nomic Embed Text v2 MoE is released under Apache 2.0, and commercial use is allowed. The license text is at https://www.apache.org/licenses/LICENSE-2.0.
What can Nomic Embed Text v2 MoE embed?
Text input, per the provider. It is documented as multilingual.
Sources
Last verified from the pages below.
- Hugging Face model card - huggingface.co
- Hugging Face API (safetensors, cardData) - huggingface.co
Other open-weight embedding models
Default dimensions and max input tokens for the other models you can run yourself.
- Nemotron 3.5 Embed 8B4,096 dims - 32,768 tokens - Self-hosted
- Qwen3-Embedding-8B4,096 dims - 32,768 tokens - Self-hosted
- Qwen3-Embedding-4B2,560 dims - 32,768 tokens - Self-hosted
- EmbeddingGemma 2768 dims - 8,192 tokens - Self-hosted
- Qwen3-Embedding-0.6B1,024 dims - 32,768 tokens - Self-hosted
- Voyage 4 Nano1,024 dims - 32,000 tokens - Self-hosted
- Granite Embedding 311M Multilingual R2768 dims - 32,768 tokens - Self-hosted
- GTE ModernBERT Base768 dims - 8,192 tokens - Self-hosted
- BGE-M31,024 dims - 8,192 tokens - Self-hosted
All embedding models - Open-weight embedding models
Newsletter
New models, every week
One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.
Keep exploring
Model API pricing and specs
First-party prices per 1M tokens for chat and reasoning models.
Local models
Open-weight LLMs you can download and run, with sizes and licenses.
What is RAG?
Where embeddings fit in a retrieval pipeline, end to end.
Vector databases compared
Where the vectors go once you have picked a model.