verifier.org

Cohere Embed v4 alternatives

11 tools we tested head to head against Cohere Embed v4, ranked — and what each one actually does differently.

last reviewed 21 aug 2026 · from our best 12 embedding models ·list curated by Onur Ozcanxin

first — what you'd be leaving

Cohere Embed v4 ranks #5 of 12 in our embedding models testing. 128k of context, text and pdfs in one space, and no published price.

78/100

by far the longest context here and genuine text-plus-pdf embedding — from the only vendor in this ranking that will not tell you what an api call costs.

why people look for an alternative
  • −no per-token api price published anywhere on cohere.com
  • −only dedicated-instance pricing is public, from $2,500 a month
  • −no MTEB score on its own pages, and third-party figures disagree
  • −no language count stated for v4.0 specifically

stay with Cohere Embed v4 if 128,000-token context — fifteen times OpenAI's, the longest here by far is the thing you care about most — nothing below beats it on that.

the short version
best alternativeQwen3-Embedding-8Bmultilingual retrieval where the licence has to be clean and the bill has to be small89/100best free optionStellaenglish-only retrieval where you want mit weights and full control of index size68/100
advertisement
  1. 1

    Qwen3-Embedding-8B

    #1 in embedding models · apache-2.0, best open multilingual quality, and a tenth of a cent hosted

    89/100

    verdictthe best combination of open licence, multilingual quality and truncatable dimensions in the category — provided you can afford to serve an 8b model or are happy renting one.

    Qwen3-Embedding-8B vs Cohere Embed v4
     Cohere Embed v4Qwen3-Embedding-8B
    pricenot published per token$0.010 / 1m tokens on DeepInfra
    free tieryesyes
    price / 1mnot published$0.010 hosted, free self-hosted
    dimensions256 / 512 / 1,024 / 1,5364,096, truncatable to 32
    context128,000 tokens32,768 tokens
    licenceproprietary apiApache-2.0
    multimodalyes — text, images, pdfsno — text only

    switch formultilingual retrieval where the licence has to be clean and the bill has to be small

    pros
    • +apache-2.0 on code and weights — commercially safe without conditions
    • +32,768-token context, four times OpenAI's or Gemini's
    • +matryoshka truncation from 4,096 down to 32 dimensions
    • +publishes MTEB scores with the board version named
    • +matching apache-2.0 reranker family
    cons
    • −8b parameters — the heaviest model here to self-host
    • −4,096 native dimensions is a large index if you do not truncate
    • −text only, no multimodal path
    visit Qwen3-Embedding-8B →full Qwen3-Embedding-8B review →
  2. 2

    gemini-embedding-2

    #2 in embedding models · one vector space for text, images, audio and video

    86/100

    verdictthe only model here that puts text, images, audio and video in one shared space — at the highest text price in the ranking, and it just invalidated its own predecessor's vectors.

    gemini-embedding-2 vs Cohere Embed v4
     Cohere Embed v4gemini-embedding-2
    pricenot published per token$0.20 / 1m text tokens
    free tieryesyes
    price / 1mnot published$0.20 text, $0.10 batch
    dimensions256 / 512 / 1,024 / 1,536128 to 3,072
    context128,000 tokens8,192 tokens
    licenceproprietary apiproprietary api
    multimodalyes — text, images, pdfsyes — text, image, audio, video

    switch forretrieval across mixed media where text-only embeddings cannot answer the question

    pros
    • +text, images, audio, video and documents in one shared vector space
    • +100+ languages, with matryoshka dimensions from 128 to 3,072
    • +batch mode halves the text rate to $0.10 per million
    • +8,192-token context, four times its own predecessor
    cons
    • −$0.20 per million is the highest text rate in the ranking
    • −audio costs 32x and video 60x the text rate
    • −vectors are incompatible with gemini-embedding-001 — upgrading means re-embedding everything
    • −no MTEB score published for this version yet
    visit gemini-embedding-2 →full gemini-embedding-2 review →
  3. 3

    text-embedding-3-large

    #3 in embedding models · the default everyone reaches for, and it is showing its age

    83/100

    verdictstill a solid general-purpose embedding with the most flexible dimension control here — on an 8k context and a model that has not been updated since january 2024.

    text-embedding-3-large vs Cohere Embed v4
     Cohere Embed v4text-embedding-3-large
    pricenot published per token$0.13 / 1m tokens
    free tieryesno
    price / 1mnot published$0.13
    dimensions256 / 512 / 1,024 / 1,5363,072, truncatable to any size
    context128,000 tokens8,192 tokens
    licenceproprietary apiproprietary api
    multimodalyes — text, images, pdfsno — text only

    switch forteams already on the OpenAI api who want a known quantity and no new vendor

    pros
    • +arbitrary dimension truncation via the dimensions parameter, not a fixed list
    • +no new vendor if you are already on the OpenAI api
    • +extremely well documented and widely supported by every framework
    • +the cheap sibling, text-embedding-3-small, is $0.02 per million
    cons
    • −8,192-token context is joint smallest in the ranking
    • −no replacement shipped since january 2024
    • −no multilingual claim, no multimodal support, no reranker sibling
    • −quotes an MTEB score without naming the board version
    visit text-embedding-3-large →full text-embedding-3-large review →
    advertisement
  4. 4

    voyage-4-large

    #4 in embedding models · cheaper than OpenAI, four times the context, and a reranker to match

    82/100

    verdictbeats the default on price, context and reranking, from a smaller vendor that publishes less about how it performs.

    voyage-4-large vs Cohere Embed v4
     Cohere Embed v4voyage-4-large
    pricenot published per token$0.12 / 1m tokens
    free tieryesyes
    price / 1mnot published$0.12
    dimensions256 / 512 / 1,024 / 1,5361,024 default; 256 to 2,048
    context128,000 tokens32,000 tokens
    licenceproprietary apiproprietary api
    multimodalyes — text, images, pdfsunconfirmed for this model

    switch forretrieval-focused teams who want a matched embedding and reranking pair from one vendor

    pros
    • +$0.12 per million — cheaper than OpenAI and it cut price on the version bump
    • +32,000-token context, four times OpenAI's
    • +matched rerankers at $0.05 and $0.02 per million
    • +dimension options are cross-compatible within the 4 series
    cons
    • −no MTEB score published on its own pages
    • −no language count or parameter count disclosed
    • −multimodal support for this specific model is unconfirmed
    • −smaller vendor than the three above it
    visit voyage-4-large →full voyage-4-large review →
  5. 5

    EmbeddingGemma

    #6 in embedding models · the cheapest way to embed anything, if the gemma terms suit you

    75/100

    verdict300m parameters that run on a laptop at a fiftieth of Gemini's price — held back by a licence that is commercially usable but not open source.

    EmbeddingGemma vs Cohere Embed v4
     Cohere Embed v4EmbeddingGemma
    pricenot published per token$0.002 / 1m tokens on DeepInfra
    free tieryesyes
    price / 1mnot published$0.002 hosted, free self-hosted
    dimensions256 / 512 / 1,024 / 1,536768, truncatable to 128
    context128,000 tokens2,048 tokens
    licenceproprietary apiGemma Terms of Use
    multimodalyes — text, images, pdfsno — text only

    switch foron-device and high-volume embedding where size and cost dominate everything else

    pros
    • +$0.002 per million hosted — the cheapest rate in the ranking
    • +300m parameters, genuinely runs on a laptop or phone
    • +matryoshka truncation to 512, 256 or 128 dimensions
    • +publishes MTEB scores with the board version named
    cons
    • −Gemma Terms of Use, not an osi licence — prohibited-use policy attached
    • −redistribution obliges you to pass the same restrictions downstream
    • −2,048-token context is among the shortest here
    • −quality sits below the larger open models, as expected at 300m
    visit EmbeddingGemma →full EmbeddingGemma review →
  6. 6

    BGE-M3

    #7 in embedding models · mit, three retrieval modes in one model, and quietly ageing

    73/100

    verdictthe most versatile open model here — dense, sparse and multi-vector output under mit — on a card that has barely moved since 2024.

    BGE-M3 vs Cohere Embed v4
     Cohere Embed v4BGE-M3
    pricenot published per token$0.010 / 1m tokens on DeepInfra
    free tieryesyes
    price / 1mnot published$0.010 hosted, free self-hosted
    dimensions256 / 512 / 1,024 / 1,5361,024, fixed
    context128,000 tokens8,192 tokens
    licenceproprietary apiMIT
    multimodalyes — text, images, pdfsno — text only

    switch forhybrid retrieval where you want dense and sparse vectors from a single model

    pros
    • +mit licensed — the most permissive terms in the ranking
    • +dense, sparse and multi-vector retrieval from one model
    • +100+ languages at 8,192 tokens of context
    • +matching bge-reranker-v2 family under the same licence
    cons
    • −fixed 1,024 dimensions with no matryoshka truncation
    • −card essentially unchanged since july 2024
    • −NVIDIA NIM is deprecating its hosted endpoint in august 2026
    • −no MTEB score with an identifiable board version
    visit BGE-M3 →full BGE-M3 review →
  7. 7

    Stella

    #8 in embedding models · mit weights with dimensions from 256 to 8,192, english only

    68/100

    verdictthe widest dimension range in the category under an unrestricted mit licence — english-only, short-context, and with nobody hosting it for you.

    Stella vs Cohere Embed v4
     Cohere Embed v4Stella
    pricenot published per tokenfree — self-host only
    free tieryesyes
    price / 1mnot publishedfree — self-host only
    dimensions256 / 512 / 1,024 / 1,536256 to 8,192
    context128,000 tokens512 tokens recommended
    licenceproprietary apiMIT
    multimodalyes — text, images, pdfsno — text only

    switch forenglish-only retrieval where you want mit weights and full control of index size

    pros
    • +mit licensed with no usage conditions whatsoever
    • +eight matryoshka dimension options from 256 to 8,192
    • +the authors state where quality plateaus, rather than leaving you to test
    • +1.5b parameters — far lighter to serve than Qwen3-8B
    cons
    • −english only
    • −512-token recommended input, the shortest here
    • −no hosted option we could price — self-host or nothing
    • −licence comes from card metadata; the repo licence file 404s
    visit Stella →full Stella review →
  8. 8

    Nomic Embed Text v2

    #9 in embedding models · a mixture-of-experts embedder that only wakes up two thirds of itself

    66/100

    verdicta clever, genuinely open, efficient multilingual model undone for most rag work by a 512-token context.

    Nomic Embed Text v2 vs Cohere Embed v4
     Cohere Embed v4Nomic Embed Text v2
    pricenot published per tokenfree — self-host
    free tieryesyes
    price / 1mnot publishedfree — self-host
    dimensions256 / 512 / 1,024 / 1,536768, truncatable to 256
    context128,000 tokens512 tokens
    licenceproprietary apiApache-2.0
    multimodalyes — text, images, pdfsno — text only

    switch forself-hosted multilingual embedding on constrained compute

    pros
    • +apache-2.0 weights with no commercial conditions
    • +mixture-of-experts design activates only 305m of 475m parameters
    • +around 100 languages from a very small model
    • +matryoshka truncation from 768 to 256 dimensions
    cons
    • −512-token context makes it unsuitable for document retrieval
    • −no hosted list price confirmable from a primary source
    • −no MTEB score published on the model card
    • −no reranker sibling
    visit Nomic Embed Text v2 →full Nomic Embed Text v2 review →
  9. 9

    Mistral Embed

    #10 in embedding models · a flat price, a tidy api, and almost no published specification

    62/100

    verdictcheaper than OpenAI and easy to adopt if you are already a Mistral customer — from a model that publishes neither its dimensions nor its benchmark scores.

    Mistral Embed vs Cohere Embed v4
     Cohere Embed v4Mistral Embed
    pricenot published per token$0.10 / 1m tokens
    free tieryesyes
    price / 1mnot published$0.10
    dimensions256 / 512 / 1,024 / 1,536not published by vendor
    context128,000 tokens8,000 tokens
    licenceproprietary apiproprietary api
    multimodalyes — text, images, pdfsno — text and code

    switch forteams already building on Mistral who want embeddings on the same bill

    pros
    • +$0.10 per million, cheaper than OpenAI's flagship
    • +no new vendor if you are already using the Mistral api
    • +flat pricing with no tiers or dimension-based surcharges
    • +a separate Codestral Embed exists for code retrieval
    cons
    • −output dimensions are not published by the vendor
    • −no parameter count, language count or MTEB score published
    • −dates to december 2023 — the oldest model in this ranking
    • −no weights, no self-host path, no reranker sibling
    visit Mistral Embed →full Mistral Embed review →
  10. 10

    Jina Embeddings v5

    #11 in embedding models · excellent quality per parameter, on weights you may not use commercially

    58/100

    verdicta genuinely strong sub-1b multilingual model that most readers of this page cannot legally deploy — and the licence is not what its reputation suggests.

    Jina Embeddings v5 vs Cohere Embed v4
     Cohere Embed v4Jina Embeddings v5
    pricenot published per tokennot published per token
    free tieryesyes
    price / 1mnot publishednot published
    dimensions256 / 512 / 1,024 / 1,5361,024, truncatable to 32
    context128,000 tokens32,768 tokens
    licenceproprietary apiCC-BY-NC-4.0 — non-commercial
    multimodalyes — text, images, pdfsno — v5-omni is a separate model

    switch forresearch and evaluation work where the non-commercial terms are not a problem

    pros
    • +677m parameters with 32,768 tokens of context
    • +matryoshka truncation from 1,024 down to 32 dimensions
    • +93 languages claimed from a sub-billion-parameter model
    • +a separate v5-omni line covers images, audio, video and pdfs
    cons
    • −weights are CC-BY-NC-4.0 — commercial use prohibited without a separate licence
    • −v4 was non-commercial too, under a qwen research licence
    • −no per-token price published for the hosted api
    • −the v4-to-v5 split moved multimodality to a different model line
    visit Jina Embeddings v5 →full Jina Embeddings v5 review →
+ 1 more tested, not detailed here
we ranked 12 embedding models in total. the 1 that didn't make this page are written up in the full ranking →

how these were compared

every tool on this page went through the same test as Cohere Embed v4 — same tasks, same order, scored the same way. the comparison tables are the figures from that testing, not vendor spec sheets.

the embedding models test in full →
was this useful?