Niches · Embeddings & rerankers

Rerank first-stage results before they reach the model

Two or three companies' docs show a full fit.

2companies, full fit
3companies, fit with a limit
14companies carry the tag
8share of the category's work
7first-hand accounts

What counts as done

One call takes the query and all candidates and returns each candidate's index with a relevance score, sorted or sortable, with a documented per-document token limit and truncation behaviour and a published billing unit.

Measured, for our own tests: 50 candidates reranked within 1 second at p95, and nDCG@10 above the first-stage order on the labelled set. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: rerank these results, which of these chunks answers the question, improve the precision of my RAG, sort these 50 passages by relevance

Does the job 2

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Jina Embeddings and Reranker B
Jina AI GmbH
POST /v1/rerank returns candidates sorted by relevance_score with their index, top_n is optional, max_doc_length defaults to 8,192 on v3.5 in a 131,072-token window, and the catalogue bills $0.05 per million tokens. p95 and nDCG unmeasured. source
Voyage AI embeddings and rerankers B
Voyage AI Innovations, Inc.
One rerank call takes a query and up to 1,000 documents, with top_k, per-model query and query-plus-document token limits, truncation true or false documented, and per-token prices. p95 and nDCG unmeasured. source

Does the job, with a limit 3

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Cohere Embed and Rerank BB
Cohere Inc.
One call returns index and relevance_score with top_n; max_tokens_per_doc defaults to 4,096 and truncates silently, and the billing unit is unclear, with billed_units carrying both tokens and search_units. Accounts report large quality gains. source
NVIDIA NeMo Retriever Embedding and Reranking NIMs B
NVIDIA Corporation
/v1/ranking scores up to 512 passages in one call and returns index and logit sorted descending, with truncate NONE or END documented, but there is no top-n field and billing is per GPU, not per call. source
ZeroEntropy zerank and zembed F
ZeroEntropy, Inc.
The hosted rerank endpoint is gone. zerank-2 is Apache 2.0 with a Sentence Transformers route and 32,768-token context, but a May 2026 breaking change made predict() return raw logits, and no per-call limits or billing remain. source

Doesn't do this job 14

Listings in the category that do something else, with the reason.

ListingWhy
Amazon Nova Multimodal Embeddings BB
Amazon Web Services, Inc.
An embedding model only; no rerank call in the Nova guide or schema. source
EmbeddingGemma 2 B
Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)
An embedding model; no reranking head or scoring mode. source
EmbeddingGemma 300M D
Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)
An embedding model; no reranking mode. source
Gemini Embedding B
Google LLC
No rerank endpoint in the embeddings guide or model page. source
Granite Embedding Small English R2 E
International Business Machines Corporation
A bi-encoder only; no reranking mode in this listing. source
jina-embeddings-v5-omni-small D
Jina AI GmbH, a subsidiary of Elastic N.V. (per the jina-embeddings listing's 2 October 2026 check)
An embedding model; no reranking head. source
Mistral Embed and Codestral Embed B
Mistral AI (RCS Paris 952 418 325)
No rerank endpoint in the OpenAPI document. source
Nomic Embed E
Nomic, Inc.
No rerank endpoint in the API reference. source
OpenAI embeddings BB
OpenAI OpCo, LLC
No rerank endpoint. source
Qwen3-Embedding-0.6B B
Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check)
An embedding model; the Qwen3-Reranker models are separate repositories, not this listing. source
Qwen3-Embedding-4B BB
Alibaba Cloud (named in the copyright line of the 8B sibling's Apache 2.0 licence; this repository has no LICENSE file)
An embedding model; the Qwen3-Reranker models are separate repositories, not this listing. source
Qwen3-Embedding-8B BB
Alibaba Cloud (named in the licence's copyright line)
An embedding model; the Qwen3-Reranker models are separate repositories, not this listing. source
Qwen3-VL-Embedding-2B C
Alibaba Cloud (RDAP names Alibaba Cloud (Singapore) Private Limited as the registrant of qwen.ai)
An embedding model; the Qwen3-VL-Reranker models are separate repositories, not this listing. source
Qwen3-VL-Embedding-8B B
Alibaba Group (Tongyi Lab, named in the copyright line of the GitHub repository's Apache 2.0 licence)
An embedding model; the Qwen3-VL-Reranker models are separate repositories, not this listing. source

What stops agents finishing

  • default per-document token cap truncates long chunks (Cohere max_tokens_per_doc 4,096)
  • no top-n field, so the agent must sort and cut (NeMo Retriever /v1/ranking)
  • billing unit unclear (searches against tokens)
  • the reranker only reorders what the candidate stage found

Around it

Before: vector-search.hybrid-keyword, embeddings.index-docs-for-rag. After: company-knowledge.cited-answer.

Where this comes from

Weight 8 of 100 in Embeddings & rerankers: 7 of 62 accounts (91 account-use-case tags, accounts counted in each use case they fit, scaled to 100 and rounded by hand); every account that tried a reranker called it a large gain; fewer accounts than its importance in threads suggests, so held at the count

The same as data: /api/v1/use-cases/embeddings.rerank-candidates.json, or the MCP tool get_use_case with id embeddings.rerank-candidates. Other jobs in this category: /api/v1/niches?category=embeddings.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

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.