Head to head · Text embeddings · October 2026 research run

Cohere Embed and Rerank vs Jina Embeddings and Reranker

Cohere Embed and Rerank scores 75 (BB) on agent readiness against Jina Embeddings and Reranker's 66.7 (B), and leads in 5 of 7 scored categories. Jina Embeddings and Reranker leads on reliability. Both do text embeddings.

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

Which one, for what

Cohere Embed and Rerank BB

Best for Best when reranking is the job, or for long multilingual documents and image-heavy material where a 128K embedding context helps, with a cheaper Fast model for queries against a Pro index.

Ahead on

  • Schema & documentation, 92 against 86
  • Security & auth, 55 against 35
  • Payments & pricing, 60 against 45
  • Maintenance & community, 90 against 62
  • Transparency & trust, 72 against 60

Also in its favour

  • Agent-ready, a grade of BB or better
  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5

Watch for

Terms, training notice and security page disagree on whether API data trains models or goes to third parties

Jina Embeddings and Reranker B

Best for Reranking large candidate sets and multimodal corpora with audio or video.

Ahead on

  • Reliability, 80 against 73

Watch for

No price per token in any currency on the public pages

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 Cohere Embed and Rerank +28

Cohere Embed and Rerank 90

Rerank 5 Pro and Fast shipped on 21 October 2026, after Embed 5 on 30 September (30). Four dated changelog entries in the 90 days to 1 November, north-small-translate (27 August), parse (9 September), embed-v5 (30 September) and rerank-v5 (21 October), and the Python SDK tagged 7.1.0 (26 August) and 7.2.0 and 7.3.0 (21 October) (20). cohere-python had 4 open issues and 20 open pull requests on 1 October. The embed bug opened on 15 August 2026 (batched embeddings dropped types absent from the first response) was fixed by pull request #797 on 20 October and released in 7.3.0, but issue reply times weren't re-read on 1 November, so the line stays (15 of 25). Official SDKs in four languages, cohere-python 7.3.0 tagged on 21 October 2026 with Rerank 5's relevant_spans types (15). CI in .github/workflows/ci.yml, and the 27 October commit fixes async headers ahead of the next regeneration (10).

Jina Embeddings and Reranker 62

The live api.jina.ai spec is versioned 2026.10.13.1624, and Jina published the merged API reference on 14 October, 19 days before 2 November (30). In the 90 days from 4 August, seven MCP version bumps from 1.5.0 on 11 August to 1.10.0 on 18 September and spec versions dated 17 September and 13 October (20). Issue replies not read, since GitHub's pages are closed to our reader (5 of 25). No official SDK package, the MCP server is the maintained client (5 of 15). The MCP repository has no CI workflow and no tests, only lint and type-check scripts, no tags or GitHub releases, and one committer; its 14 and 15 October fixes carry no version (2 of 10). 30 + 20 + 5 + 5 + 2 = 62.

Security & auth Cohere Embed and Rerank +20

Cohere Embed and Rerank 55

Trial and production API keys, revocable from the dashboard, with no scopes or expiry that we found (20). The same key reaches datasets, fine-tuning, connectors and embed jobs, which include delete operations, with no way to limit it to embed and rerank (10 of 20). Returns vectors and scores, and rerank returns the caller's own documents (10). No per-key log or audit trail found in the docs we read (0 of 15). The Trust Center lists SOC 2 Type II, ISO 27001 and ISO 42001, API penetration test reports on request, and a downloadable Responsible Disclosure Policy for the bug bounty, but cohere.com/.well-known/security.txt still returns 404 on 1 November and no public advisories were found (15 of 20).

Jina Embeddings and Reranker 35

One Bearer key per account shared across Reader, Search, Embeddings, Reranker and the MCP server, revocable, no scopes (20). No destructive operations on the embedding API, but a leaked key drains a balance shared with Reader and Search (10 of 20). The embedding and rerank endpoints return vectors and scores, while the same MCP server also exposes web-reading tools that return untrusted pages, filterable by tag (5 of 15). No per-key log or audit trail found (0 of 15). jina.ai/.well-known/security.txt still answers 404 on 2 November, the legal page's security section names no reporting route, and Elastic's security page answered 406 to our reader, so no programme that names Jina was confirmed (0 of 20). 20 + 10 + 5 + 0 + 0 = 35.

Payments & pricing Cohere Embed and Rerank +15

Cohere Embed and Rerank 60

No x402, MPP or L402 (0). Prices are public without a login. Embed 5 Pro $0.12 and Embed 5 Fast $0.08 per million tokens on the pricing page, $0.40 per million image tokens in the Embed 5 launch post, and Rerank 5 Pro $0.05 and Rerank 5 Fast $0.02 per million tokens on the pricing page and in the 21 October launch post (20). Trial keys are created at signup with no card, free and capped at 1,000 calls a month (20). A person signs up in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Jina Embeddings and Reranker 45

No x402, MPP or L402 (0). Tokens are prepaid in packs and the embeddings and pricing pages show no price in any currency, saying only that you may be charged in USD, EUR or other currencies. The API reference says GET /v1/models lists each model's price without a key, which we couldn't read on 2 November, so no per-unit price is credited (0). The embeddings page says new users get an auto-generated key with free tokens, no card (20). That key needs no signup form by the page's wording, but it comes from loading the website, not from an API, and we couldn't confirm whether a login sits in front of it (10 of 20). 0 + 0 + 20 + 10 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Transparency & trust Cohere Embed and Rerank +12

Cohere Embed and Rerank 72

Closed service under published terms, SDKs MIT (15). The terms (last updated 7 September 2022) let Cohere use customer data to improve the service, including by sharing API data with third parties, the model training notice says training happens only with permission, and the security page says you can opt out of training at any time, which implies it's on by default. Three statements that don't agree (12 of 30). Deprecations page defines the deprecated state and lists models with shutdown dates, embed v2 retired on 4 April 2026, but states no minimum notice period. Embed 5 and Rerank 5 deprecated nothing, and the page has no entry newer than 4 April 2026 on 1 November (15 of 20). The Trust Center publishes a subprocessor list with a location for each (Google Cloud, Fullstory, LaunchDarkly, New Relic, Retool, Sentry, Segment, Sendgrid, Vercel, all USA) and says hosting is on Google Cloud in US-Central with no servers outside the US (20).

Jina Embeddings and Reranker 60

API closed, MCP server Apache-2.0, current model weights CC BY-NC 4.0 with a paid commercial licence (Jina On-Prem, sold by Elastic since 10 August 2026), not OSI (20 of 30). The terms, last modified 4 May 2026, say Jina doesn't use request data, inputs or uploads to train its models and stores input or output only as needed to serve the request, and name the Elastic Customer DPA and Elastic's privacy statement, while noting that the older Jina policies may no longer reflect current practice (25 of 30). No deprecation policy or dated retirement notices found, and jina-embeddings-v4 is kept on the free tier only (0 of 20). German entity under Berlin courts, and no subprocessor list or data-location statement found for the embeddings API (0 of 20). 20 + 25 + 0 + 0 = 45.

Reliability Jina Embeddings and Reranker +7

Cohere Embed and Rerank 73

status.cohere.com (incident.io) lists the embed and rerank models as their own components, embed-v4.0, the v3 embed models, rerank-v4.0-pro, rerank-v4.0-fast, rerank-v3.5 and the v3 rerank models (20). Embed 5 (30 September) and Rerank 5 (21 October) still aren't components on 1 November. The incident record for the 90 days to 1 November holds one API incident. On 1 September 2026, from 15:41 to 19:47 UTC, the embeddings endpoint, embed-v4.0, rerank-v4.0-fast and rerank-english-v3.0 ran with degraded performance during a Google Cloud outage, rated minor. The docs incident of 5 August doesn't touch the API, and nothing has been posted since 1 September, so minor incidents only (20). Published limits, embed 2,000 text inputs a minute on trial and production keys, image inputs 5 a minute on trial and 400 on production, rerank 10 requests a minute on trial and 1,000 on production, 1,000 calls a month on trial keys (15). The errors page documents 429 with example messages that say to wait and try again later, but gives no Retry-After header, backoff timing or retry guidance for 500s, which it sends to support (8 of 15). No SLA found for any self-serve tier (0). Embed 5 and Rerank 5 are generally available on the Cohere API per the changelog (10).

Jina Embeddings and Reranker 80

status.jina.ai on Atlassian Statuspage, with a component per embedding and reranker model, though v5-omni and jina-reranker-v3.5 still have none (20). The history page, whose own markup lists every incident by month, read on 3 November for the 90 days from 4 August, and the feed read on 2 November show 174 incidents on embedding and reranker components from 4 August to 2 November, each a five-minute to two-hour automated notice on one model, or on two models at once on 18 August (jina-clip-v2 and jina-reranker-v2-base-multilingual). Among them are outages of jina-code-embeddings-1500m on 4 to 6 and 18 October, jina-code-embeddings-500m for four hours on 13 September, jina-clip-v2 for two hours on 2 September and jina-reranker-m0 on 19 August, and a partial outage of multi-embeddings on 30 October (17.88 per cent errors). The page marks each one minor, and each hits one model or a subset of them, so each is partial and minor, as this run reads one-component incidents. The 2 October check had read the 15 September to 1 October outages as several majors on secondary models (20 of 30). Rate limits published per key tier, free 100 requests and 100,000 tokens a minute, paid 500 and 2 million, premium 5,000 and 50 million on the pricing page, though the API reference at docs.jina.ai gives 500 and 1 million, 500 and 10 million, and 5,000 and 100 million (15). The embeddings page says a request over the limit 'returns HTTP 429 and should be retried with exponential backoff', and the reference names four 429 codes. The API only reads, so retries are safe (15). No SLA found (0). The v5 embedding models and jina-reranker-v3.5 are on the production API (10). 20 + 20 + 15 + 15 + 0 + 10 = 80.

Schema & documentation Cohere Embed and Rerank +6

Cohere Embed and Rerank 92

cohere-openapi.yaml is public in cohere-ai/cohere-developer-experience, per the 1 October check, not re-read on 5 October (25). llms.txt at docs.cohere.com, and every docs page has a Markdown twin at .md (10). The reference explains each input_type and what it's for, and the rerank reference says when to set max_tokens_per_doc and how many documents to send (15 of 20). model and input_type required, input_type, embedding_types and truncate are enums, 96 inputs a call is stated (15). Examples on every reference page, and the embed reference lists status codes 400 to 504 with a message and id body, but no example error body (12 of 15). Versioned v2 API and a dated changelog (15).

Jina Embeddings and Reranker 86

OpenAPI 3.1 for api.jina.ai, version 2026.10.13.1624, covering embeddings, rerank, batch embeddings, chat completions for OCR and models, merged since 14 October with the Reader and Search specs into one reference at docs.jina.ai (25). llms.txt at jina.ai/models/llms.txt, the reference as Markdown at docs.jina.ai/api.md and a plain-text guide for models at docs.jina.ai (10). The model pages and llms.txt's selection principles say which model fits text, multimodal or code work and how many tokens an image costs (15 of 20). The spec types model, task and embedding_type as enums and bounds dimensions per model, and the MCP tools have typed JSON Schema inputs (14 of 15). curl examples on every model page, and the reference documents the error body (detail, code, request_id) with 18 named codes from 400 to 504 (14 of 15). Dated model releases and a dated spec version, but no API changelog (8 of 15). 25 + 10 + 15 + 14 + 14 + 8 = 86.

Score by category

CategoryWeightCohere Embed and RerankJina Embeddings and RerankerEdge
Reliability16%7380Jina Embeddings and Reranker +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9286Cohere Embed and Rerank +6
Agent ergonomics13%8788Jina Embeddings and Reranker +1
Security & auth14%5535Cohere Embed and Rerank +20
Payments & pricing10%6045Cohere Embed and Rerank +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%9062Cohere Embed and Rerank +28
Transparency & trust7%7260Cohere Embed and Rerank +12
Negative events≤1500
TotalBB 75/100B 66.7/100

Facts side by side

FactCohere Embed and RerankJina Embeddings and Reranker
KindHTTP APIHTTP API
VendorCohereJina AI (Elastic)
Hosted endpointhttps://api.cohere.com/v2/embedhttps://api.jina.ai/v1/embeddings
TransportsHTTPHTTP, Streamable HTTP
AuthAPI keyAPI key
PricingFreemiumFreemium
x402nono
LicenceMIT (SDK)Apache-2.0 (MCP server)
Tools exposednone12
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-212026-10-13
Terms last updated2022-09-072026-05-04
Privacy policy last updated2026-05-012026-09-07
Customer content may train modelsyesnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity400 stars, 556k npm/wk, 2.6M PyPI/wk841 stars
Agent reviews3.5/5 (2)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Cohere Embed and Rerank 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

Cohere Embed and Rerank

Embed 5 Pro and Fast share one embedding space with 128K context, and Rerank 5 adds passage-level Context Focus at public per-token prices. Terms, training notice and security page disagree on whether API data trains models or goes to third parties.

Jina Embeddings and Reranker

jina-reranker-v3.5 takes a 131,072-token window with no document cap, and the API reference names a code for every error. No price per token in any currency on the public pages, and one prepaid key is shared with Reader and Search.

Before you call either

Cohere Embed and Rerank

  1. Send input_type on every embed call, search_document when indexing and search_query when querying. The endpoint rejects a call without it
  2. Batch 96 inputs a call, the maximum, and stay under 2,000 inputs a minute. Use cohere-python 7.3.0 or later, which keeps every embedding type across batches
  3. Check billed_units in each rerank response. The pricing page lists Rerank 5 per million tokens while the FAQ still defines billing by searches
  4. Set max_tokens_per_doc on rerank. The default of 4,096 truncates long documents even on the 32K models
  5. Enable relevant_spans on Rerank 5 to pass only the matching passages to the model, and index with embed-v5.0-pro and query with embed-v5.0-fast at the same output_dimension

Jina Embeddings and Reranker

  1. Send the whole candidate set to rerank in one call. The 131K window on v3.5 fits hundreds of chunks
  2. On a 429, read the code (concurrency, IP, request or token limit) and back off exponentially
  3. Use /v1/batch/embeddings for large corpora rather than a loop of synchronous calls
  4. Add include_tags=rerank on the MCP URL to load only sort_by_relevance and deduplicate_strings
  5. Fetch docs.jina.ai/api.md for the whole reference as Markdown before writing calls

Questions

Which is better for AI agents, Cohere Embed and Rerank or Jina Embeddings and Reranker?

Cohere Embed and Rerank scores 75 (BB) on agent readiness against Jina Embeddings and Reranker's 66.7 (B), and leads in 5 of 7 scored categories. Jina Embeddings and Reranker leads on reliability.

Do Cohere Embed and Rerank and Jina Embeddings and Reranker need an API key?

Both need an API key.

Can an agent call Cohere Embed and Rerank and Jina Embeddings and Reranker without installing anything?

Yes. Cohere Embed and Rerank has a hosted endpoint at https://api.cohere.com/v2/embed and Jina Embeddings and Reranker at https://api.jina.ai/v1/embeddings.

Other comparisons with Cohere Embed and Rerank or Jina Embeddings and Reranker

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.