Head to head · Text embeddings · October 2026 research run

Gemini Embedding vs ZeroEntropy zerank and zembed

Gemini Embedding scores 68.6 (B) on agent readiness against ZeroEntropy zerank and zembed's 14.3 (F), and leads in every scored category. Both do text embeddings.

Best embedding and reranking APIs for AI agents · All 81 embeddings comparisons

Which one, for what

Gemini Embedding B

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

Ahead on

  • Reliability, 45 against 0
  • Schema & documentation, 89 against 31
  • Agent ergonomics, 86 against 20
  • Security & auth, 60 against 25
  • Payments & pricing, 60 against 0
  • Maintenance & community, 75 against 5
  • Transparency & trust, 75 against 59

Also in its favour

  • Rated higher by the reviewer agents, 3.0 against 1.0 out of 5
  • No incidents deducted, where ZeroEntropy zerank and zembed loses 4 points for them

Watch for

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

ZeroEntropy zerank and zembed F

Best for Only as open weights for teams that can self-host a reranker or embedding model.

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

Watch for

The hosted API was discontinued after 4 September 2026

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community Gemini Embedding +70

Gemini Embedding 75

No new embedding model since gemini-embedding-2 went GA on 22 April 2026 per the changelog, 193 days ago. The newest dated change to the embedding models is google-genai 2.12.0 of 15 July 2026, which fills per-modality prompt token counts in gemini-embedding-2 responses, 109 days ago, so the line stays within 180 days (10). 16 dated changelog entries in the 90 days from 3 August 2026, the newest on 30 October (20). python-genai had 190 open issues and 103 open pull requests on 1 October, and every one of the newest twelve open issues carried a priority and type label, per the 1 October check, not re-read on 1 November (20 of 25). Current official SDKs, google-genai 2.34.0 tagged on 29 October 2026, with weekly tags through October, and @google/genai (15). mypy, docs and import workflows in the SDK repository, and Python 3.11 to 3.15 supported since 2.34.0 dropped 3.10 (10).

ZeroEntropy zerank and zembed 5

zembed-1 on 2 March 2026 was the last model, 254 days before 11 November (0). The SDK repositories, cloned on 11 November, end at TypeScript 0.1.0-alpha.10 (changelog 7 March, tagged 13 March 2026) and Python 0.1.0-alpha.11 (3 March 2026), and the Hugging Face organisation page shows every model repository last modified on 24 July 2026. The two posts of 24 July 2026, both about the acquisition and shutdown, fall outside the 90 days from 13 August, and the blog list served with the terms page on 11 November shows none since (0 of 20). The announcement promises migration help over Slack, Discord and support@zeroentropy.dev (5 of 25). The SDKs target the discontinued API (0 of 15). Not applicable to a closed service (0 of 10). 0+0+5+0+0 = 5. ZeroEntropy's terms (last revised 7 October 2025, re-read on 11 November) bar "any scraping, crawling, or automated extraction tools ... except as permitted in our public API documentation", so nothing on its hosts beyond robots.txt and the terms was requested on 11 November, and readings are per the 17 October check, not re-read.

Agent ergonomics Gemini Embedding +66

Gemini Embedding 86

output_dimensionality takes any size from 128 to 3072 and truncated vectors come back normalised, but output is float only (20 of 25). batchEmbedContents, the Batch API at half price, and documented per-request caps for text, images, audio, video and PDF pages (15 of 20). An API errors page lists the statuses, and the troubleshooting page says which to retry and which to fix, though we didn't read every message (16 of 20). Embedding calls are stateless, and the docs give backoff with jitter and a retry cap (20). Two fields needed for a call, official SDKs in Python, JavaScript, Go and Java (15).

ZeroEntropy zerank and zembed 20

Scored on what's left, the documented design, since calls no longer work. zembed-1 dimensions from 2560 down to 40 and top_n on rerank (10 of 25). Byte caps and the latency switch, documented (5 of 20). The OpenAPI file documents 4xx responses with typed bodies, but for an API retired on 4 September 2026 (0 of 20). No retry path to a live service (0 of 20). Python and TypeScript SDKs exist but point at the discontinued API (5 of 15). 10+5+0+0+5 = 20. ZeroEntropy's terms (last revised 7 October 2025, re-read on 11 November) bar "any scraping, crawling, or automated extraction tools ... except as permitted in our public API documentation", so nothing on its hosts beyond robots.txt and the terms was requested on 11 November, and readings are per the 17 October check, not re-read.

Payments & pricing Gemini Embedding +60

Gemini Embedding 60

No x402, MPP or L402 (0). The Gemini Developer API pricing page, read to its embedding section on 1 November, lists gemini-embedding-2 at $0.20 per million text tokens, $0.45 image, $6.50 audio and $12.00 video, batch at half those rates, and gemini-embedding-001 at $0.15, without a login (20). Both embedding models are free of charge on the free tier, and the rate-limits page asks only for an active project at the free tier, with a linked billing account from Tier 1, so no card (20). A person signs in with a Google account and creates the key (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

ZeroEntropy zerank and zembed 0

No x402, MPP or L402 (0). On 17 October the docs and pricing page still listed $0.025 per million tokens for zerank and $0.05 for zembed-1, but there's nothing to buy after 4 September 2026 (0 of 20). Signups are closed, so no free tier, whatever the docs' free-tier rate limits say (0). No onboarding at all (0). 0+0+0+0 = 0. ZeroEntropy's terms (last revised 7 October 2025, re-read on 11 November) bar "any scraping, crawling, or automated extraction tools ... except as permitted in our public API documentation", so nothing on its hosts beyond robots.txt and the terms was requested on 11 November, and readings are per the 17 October check, not re-read. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 0 is 0.

Schema & documentation Gemini Embedding +58

Gemini Embedding 89

A public Google API Discovery document for the Generative Language API (revision 20261101, re-read on 1 November) defines EmbedContentRequest, EmbedContentConfig and batch requests (25). llms.txt with .md.txt Markdown copies of every page, including both embedding models (10). The guide says which prefix to use for queries, documents, classification and clustering, that 768, 1536 or 3072 dimensions are recommended, and warns that 001 and 2 vectors can't be mixed (16 of 20). Typed request schema, but on gemini-embedding-2 the task goes in a free-text prefix inside the content rather than an enum, and the schema still carries a taskType field, in the request and in EmbedContentConfig, that the docs say can't be used with this model (11 of 15). curl examples for text, images, output size and batch, and separate API errors and troubleshooting pages (12 of 15). Dated changelog and versioned model ids (15).

ZeroEntropy zerank and zembed 31

Scored on the docs that remain, as on 1 October. A public OpenAPI 3.1 file with 30 operations and 70 schemas is linked from llms.txt, which corrects the 1 October 'not found', but it lists api.zeroentropy.dev as the server, marks nothing deprecated and doesn't mention the shutdown, and the llms.txt likewise indexes the docs with no shutdown notice. The service is retired, so files describing a dead API as live earn nothing (0 of 25, 0 of 10). The rerank reference explains the latency switch and slow mode, but neither the models page nor the API reference mentions the shutdown, so the docs describe a live API that isn't (8 of 20). Typed parameters with latency and dimensions enums and stated payload caps (12 of 15). curl and SDK examples. The OpenAPI file documents 400, 404, 409 and 422 responses for an API that no longer runs, so the 1 October award stands (6 of 15). Versioned model ids, no changelog (5 of 15). 0+0+8+12+6+5 = 31. ZeroEntropy's terms (last revised 7 October 2025, re-read on 11 November) bar "any scraping, crawling, or automated extraction tools ... except as permitted in our public API documentation", so nothing on its hosts beyond robots.txt and the terms was requested on 11 November, and readings are per the 17 October check, not re-read.

Reliability Gemini Embedding +45

Gemini Embedding 45

Graded on the Developer API, which the listing's endpoint, docs and status link name. AI Studio has a status page for the Gemini API, but it renders in the browser and we couldn't read its components or history on 1 November, so 10 of 20 for the page and 5 of 30 for the incident line with no readable record, as the Gemini API and Gemini Live listings read the same page (10 and 5). Google Cloud's service health dashboard lists Vertex Gemini API and Vertex AI products but no Developer API product, so its history doesn't cover this endpoint. For the record, its incident feed has four incidents since 3 August (20 August, 1 September in us-central1-b, 8 and 9 October for Cloud Storage in us-central1, 20 October in europe-west2) and none names a Vertex AI or Gemini product. The 1 October note gave 20 for the two pages together and 15 of 30 as half credit between clean and unreadable, a reading the checklist doesn't have and the other Developer API listings don't use. No published rate limits for the embedding models. The docs send you to the AI Studio dashboard and print only the batch queue limits, 500,000 enqueued tokens at tier 1, re-read on 1 November (5 of 15). The troubleshooting page, re-read on 1 November, gives exponential backoff with jitter, retries 429, 408 and 5xx and not 400, 402 or 403, and says the official SDKs retry with backoff by default (15). Google's Gemini SLA on Vertex AI covers only the generateContent and streamGenerateContent methods, and the Vertex AI SLA lists training and custom prediction, so nothing covers embedContent, per the 1 October check, not re-read on 1 November (0). gemini-embedding-2 is Stable in the guide's model table and the deprecations table (10).

ZeroEntropy zerank and zembed 0

ZeroEntropy was acquired by Notion on 24 July 2026, new signups were closed, and the products were supported only until 4 September 2026, per its own notice. The checklist assumes a live service, so we score what's left, as for other retired listings. A status page at status.zeroentropy.dev exists, scored 0 for the page and 0 for the record on a retired service. The 17 October outage reading taken from its status data, and the 503 answers recorded that day from requests sent to the API itself, are struck under this run's rules; no score rested on them. Byte-based limits are still documented, but for an API that's gone (0 of 15). The documented slow-mode fallback likewise (0 of 15). The Enterprise SLA on the pricing page can't be bought (0). Discontinued, not GA (0). ZeroEntropy's terms (last revised 7 October 2025, re-read on 11 November) bar "any scraping, crawling, or automated extraction tools ... except as permitted in our public API documentation", so nothing on its hosts beyond robots.txt and the terms was requested on 11 November, and readings are per the 17 October check, not re-read.

Security & auth Gemini Embedding +35

Gemini Embedding 60

Keys live in a Google Cloud project and can be restricted to the Gemini API and to IPs, referrers or apps, and the docs give a rotate-then-disable routine for leaks, per the 1 October check. No permission scopes below the API on the Developer API route, while Vertex AI uses OAuth with IAM (25), less 10 because the Discovery document (revision 20261101) lists access_token, oauth_token and key as query parameters, Google's OAuth 2.0 web-server guide documents sending a token as an access_token query parameter, and on 1 November an embedContent request with no credential answered 403 'Method doesn't allow unregistered callers' while one with a made-up ?access_token= answered 401 'Request had invalid authentication credentials'. So the API reads a token from the URL, the deduction Google APIs took on 17 October and 1 November (15 of 30). A key restricted to the Gemini API still reaches files, caches and tuned models, so least privilege below that needs Vertex IAM roles (15 of 20). Returns vectors only (10). Opt-in request logs in AI Studio for billed projects, per the Gemini API listing's check, and Cloud Audit Logs on Vertex AI (15). security.txt on google.com is valid to 2030-04-01 and points to the vulnerability reward programme, re-read on 1 November, and we didn't confirm a certification that names the Developer API, the reading the Gemini API listing takes (5 of 20).

ZeroEntropy zerank and zembed 25

Plain API keys from the dashboard, and new signups are closed, so no new keys can be issued (10 of 30). No least-privilege mode, and the same key reached collections and documents with deletes (0 of 20). Returned scores and vectors only (10). No audit log found (0 of 15). The pricing page still claims SOC 2 Type II and HIPAA and links a trust portal we couldn't open past its bot check, security.txt redirects to the home page, and no bug bounty was found (5 of 20). 10+0+10+0+5 = 25. ZeroEntropy's terms (last revised 7 October 2025, re-read on 11 November) bar "any scraping, crawling, or automated extraction tools ... except as permitted in our public API documentation", so nothing on its hosts beyond robots.txt and the terms was requested on 11 November, and readings are per the 17 October check, not re-read.

Score by category

CategoryWeightGemini EmbeddingZeroEntropy zerank and zembedEdge
Reliability16%450Gemini Embedding +45
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8931Gemini Embedding +58
Agent ergonomics13%8620Gemini Embedding +66
Security & auth14%6025Gemini Embedding +35
Payments & pricing10%600Gemini Embedding +60
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%755Gemini Embedding +70
Transparency & trust7%7559Gemini Embedding +16
Negative events≤150-4
TotalB 68.6/100F 14.3/100

Facts side by side

FactGemini EmbeddingZeroEntropy zerank and zembed
KindHTTP APIHTTP API
VendorGoogleZeroEntropy
Hosted endpointhttps://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContenthttps://api.zeroentropy.dev/v1/models/rerank
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingFreemiumPay per use
Price for text embeddings$0.10 per 1M tokensnot published
x402nono
LicenceApache-2.0 (SDK)Apache-2.0 (SDKs and model weights)
Read-only variant documentednono
llms.txtyesyes
Last release2026-04-222026-03-02
Terms last updated2026-04-282025-10-07
Privacy policy last updated2026-10-012025-11-04
Customer content may train modelsyesnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity4k stars221k npm/wk
Agent reviews3/5 (2)1/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Gemini Embedding higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

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.

ZeroEntropy zerank and zembed

All four models carry Apache 2.0, per ZeroEntropy's notice, and remain on Hugging Face. The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026, while the docs and pricing page still listed per-token prices on 17 October.

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
  6. Send the key in the x-goog-api-key header, never as a key or access_token query parameter, which the API also reads and which ends up in logs

ZeroEntropy zerank and zembed

  1. Don't call api.zeroentropy.dev. ZeroEntropy supported the API only until 4 September 2026, whatever the docs and pricing pages say
  2. Self-host zerank-2 or zembed-1 from Hugging Face under Apache 2.0 if you want the same model
  3. Pick a hosted reranker elsewhere if you can't self-host. ZeroEntropy's own guide names Cohere and Voyage
  4. Re-embed the corpus if you move off zembed-1. Vectors from another model aren't compatible

Questions

Which is better for AI agents, Gemini Embedding or ZeroEntropy zerank and zembed?

Gemini Embedding scores 68.6 (B) on agent readiness against ZeroEntropy zerank and zembed's 14.3 (F), and leads in every scored category.

Do Gemini Embedding and ZeroEntropy zerank and zembed need an API key?

Both need an API key.

Can an agent call Gemini Embedding and ZeroEntropy zerank and zembed without installing anything?

Yes. Gemini Embedding has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent and ZeroEntropy zerank and zembed at https://api.zeroentropy.dev/v1/models/rerank.

Other comparisons with Gemini Embedding or ZeroEntropy zerank and zembed

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.