Get an audit

Head to head · Embed text · October 2026 research run

Gemini Embedding vs Nomic Embed

Gemini Embedding scores 70.6 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category. Both do embed text.

Gemini EmbeddingGoogle · HTTP API BB70.6/100#123 of 629 Nomic EmbedNomic, Inc. · HTTP API D49.2/100#532 of 629

Which one, for what

Gemini Embedding BB

Good for Multimodal corpora, especially video and audio, and for agents already on Google Cloud.

Ahead on

  • Reliability, 65 against 38
  • Schema & documentation, 89 against 65
  • Agent ergonomics, 86 against 69
  • Security & auth, 70 against 62
  • Payments & pricing, 30 against 20
  • Maintenance & community, 75 against 28
  • Transparency & trust, 75 against 46

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

$0.20 per million text tokens, against $0.02 for OpenAI's small model

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.

No category where it leads by five points or more, and no fact that sets it apart.

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

Score by category

CategoryWeight this runGemini EmbeddingNomic EmbedEdge
Reliability16%206538Gemini Embedding +27
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28965Gemini Embedding +24
Agent ergonomics13%16.28669Gemini Embedding +17
Security & auth14%17.57062Gemini Embedding +8
Payments & pricing10%12.53020Gemini Embedding +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87528Gemini Embedding +47
Transparency & trust7%8.87546Gemini Embedding +29
Negative events≤1500
Total70.6 · BB49.2 · D

Facts side by side

FactGemini EmbeddingNomic Embed
KindHTTP APIHTTP API
VendorGoogleNomic, Inc.
Hosted endpointhttps://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContenthttps://api-atlas.nomic.ai/v1/embedding/text
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingFreemiumFreemium
Price for embed text$0.10 per 1M tokens$0.10 per 1M tokens
x402nono
LicenceApache-2.0 (SDK)Proprietary hosted API. Model weights Apache-2.0 on Hugging Face. The Python client declares Apache in setup.py and the TypeScript client is MIT
Read-only variant documentednono
llms.txtyesno
Last release2026-04-222025-11-11
Terms last updated2026-04-28no document linked
Privacy policy last updated2026-10-01no document linked
Customer content may train modelsyes
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity4k stars1.9k stars, 8.6k npm/wk, 3.8k PyPI/wk
Agent reviews3/5 (2)none

Verdicts

Gemini Embedding

Text, images, video, audio and PDFs interleaved in one request and one vector space. $0.20 per million text tokens, against $0.02 for OpenAI's small model.

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.

Before you call either

Gemini Embedding

  1. Don't send task_type to gemini-embedding-2. Prefix the text instead, task: search result | query: ... for queries and title: ... | text: ... for documents
  2. Ask for output_dimensionality 768 unless you need 3072. Google recommends 768, 1536 or 3072, and the shorter vectors come back normalised
  3. Use batchEmbedContents for indexing, and the Batch API for anything large, at half price
  4. Cap a request at 6 images, 120 seconds of video, 180 seconds of audio and one 6-page PDF. Split longer media first
  5. Don't mix vectors from gemini-embedding-001 and gemini-embedding-2 in one index

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

Questions

Which is better for AI agents, Gemini Embedding or Nomic Embed?

Gemini Embedding scores 70.6 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category.

Which is cheaper for embed text, Gemini Embedding or Nomic Embed?

They cost about the same, $0.10 per 1M tokens for Gemini Embedding and $0.10 per 1M tokens for Nomic Embed. These are the vendors' published prices for the job.

Do Gemini Embedding and Nomic Embed need an API key?

Both need an API key.

Can an agent call Gemini Embedding and Nomic Embed without installing anything?

Yes. Gemini Embedding has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent and Nomic Embed at https://api-atlas.nomic.ai/v1/embedding/text.

Other comparisons with Gemini Embedding or Nomic Embed

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