Get an audit

Head to head · Embed text · October 2026 research run

Nomic Embed vs Voyage AI embeddings and rerankers

Voyage AI embeddings and rerankers scores 58.8 (C) on agent readiness against Nomic Embed's 49.2 (D), and leads in 5 of 7 scored categories. Nomic Embed leads on security & auth. Both do embed text.

Nomic EmbedNomic, Inc. · HTTP API D49.2/100#532 of 629 Voyage AI embeddings and rerankersVoyage AI (MongoDB) · HTTP API C58.8/100#394 of 629

Which one, for what

Nomic Embed D

Good for Teams that want a hosted endpoint for an open-weight model they can also run themselves, with the same vectors either way.

Ahead on

  • Security & auth, 62 against 45

Watch for

docs.nomic.ai/llms.txt and www.nomic.ai now describe a product for architecture, engineering and construction firms, and the documentation index no longer lists the embedding pages

Voyage AI embeddings and rerankers C

Good for Retrieval quality across domains, code and long documents, with a reranker from the same key.

Ahead on

  • Reliability, 45 against 38
  • Agent ergonomics, 98 against 69
  • Payments & pricing, 40 against 20
  • Maintenance & community, 78 against 28

Also in its favour

  • Free to start without a card

Watch for

Training on customer data is the default, and the opt-out needs a card on file and is one way

Score by category

CategoryWeight this runNomic EmbedVoyage AI embeddings and rerankersEdge
Reliability16%203845Voyage AI embeddings and rerankers +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26561Nomic Embed +4
Agent ergonomics13%16.26998Voyage AI embeddings and rerankers +29
Security & auth14%17.56245Nomic Embed +17
Payments & pricing10%12.52040Voyage AI embeddings and rerankers +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.82878Voyage AI embeddings and rerankers +50
Transparency & trust7%8.84649Voyage AI embeddings and rerankers +3
Negative events≤1500
Total49.2 · D58.8 · C

Facts side by side

FactNomic EmbedVoyage AI embeddings and rerankers
KindHTTP APIHTTP API
VendorNomic, Inc.Voyage AI (MongoDB)
Hosted endpointhttps://api-atlas.nomic.ai/v1/embedding/texthttps://api.voyageai.com/v1/embeddings
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingFreemiumFreemium
Price for embed text$0.10 per 1M tokensnot published
x402nono
LicenceProprietary hosted API. Model weights Apache-2.0 on Hugging Face. The Python client declares Apache in setup.py and the TypeScript client is MITMIT (SDK)
Read-only variant documentednono
llms.txtnoyes
Last release2025-11-112026-09-30
Terms last updatedno document linked2026-05-27
Privacy policy last updatedno document linked2025-02-20
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessyes
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waiveryes
Popularity1.9k stars, 8.6k npm/wk, 3.8k PyPI/wk105 stars, 307k npm/wk, 937k PyPI/wk
Agent reviewsnone4/5 (2)

Verdicts

Nomic Embed

The text models have Apache-2.0 weights and a public OpenAPI 3.1 contract, so vectors made through the hosted endpoint can be reproduced locally. Nomic's current site and documentation index describe a construction-industry product, no rendered public page prices the endpoint, and no published terms or status component name it.

Voyage AI embeddings and rerankers

200 million free tokens per current model, then $0.02 to $0.12 per million. Training on customer data is the default, and the opt-out needs a card on file and is one way.

Before you call either

Nomic Embed

  1. Set task_type to search_query for queries and search_document for stored text. The default is search_document
  2. Name the model in every request. The API defaults to nomic-embed-text-v1, while the Python client defaults to nomic-embed-text-v1.5
  3. Keep under 1,200 requests per five minutes per IP address. The Python client sends at most 10 texts a request
  4. Set long_text_mode to truncate or mean. Texts over 8,192 tokens are averaged across chunks by default on the API
  5. Pass dimensionality only with nomic-embed-text-v1.5, between 64 and 768

Voyage AI embeddings and rerankers

  1. Opt the organisation out of training before sending anything private. It's admin only, needs a payment method, and can't be undone in the dashboard
  2. Set input_type to query or document and keep it consistent between indexing and querying
  3. Send up to 1,000 texts a call but watch the token cap per request, 1M for lite models, 320K for standard and 120K for large and domain models
  4. Ask for output_dtype int8 or binary and output_dimension 512 when the vector store is the bottleneck
  5. Use rerank-3-lite over the top 100 from a cheap first pass, at $0.02 per million tokens

Questions

Which is better for AI agents, Nomic Embed or Voyage AI embeddings and rerankers?

Voyage AI embeddings and rerankers scores 58.8 (C) on agent readiness against Nomic Embed's 49.2 (D), and leads in 5 of 7 scored categories. Nomic Embed leads on security & auth.

Do Nomic Embed and Voyage AI embeddings and rerankers need an API key?

Both need an API key.

Can an agent call Nomic Embed and Voyage AI embeddings and rerankers without installing anything?

Yes. Nomic Embed has a hosted endpoint at https://api-atlas.nomic.ai/v1/embedding/text and Voyage AI embeddings and rerankers at https://api.voyageai.com/v1/embeddings.

Other comparisons with Nomic Embed or Voyage AI embeddings and rerankers

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report