Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Mixedbread rerankers - verified

Mixedbread reranker models

Mixedbread: 5 reranker models, read from the provider's own pages on October 18, 2026, 1 of them an older model still served, 3 with open weights. Mixedbread rerankers are sold as a rerank add-on to Store queries, from +$3.50 per 1K queries (rerank add-on to $4 per 1K semantic Store queries) for all 2 models and self-hosted from open weights, with no per-call price.

Read from mixedbread.com, huggingface.co. Compare every reranker

Models
5
Current
4
Older
1
Open weights
3

Billing and caveats

Mixedbread

Mixedbread no longer documents a standalone rerank endpoint; reranking is a search option on its Stores API, and rerank pricing is an add-on per 1K Store queries.

Current models

mxbai-rerank-v3.1-listwise

mixedbread-ai/mxbai-rerank-v3.1-listwise - API - Add-on per 1K Store queries

GA
Price (provider's unit)

+$3.50 per 1K queries (rerank add-on to $4 per 1K semantic Store queries)

“Semantic: Fine-grained semantic retrieval · $4 +$3.50 with rerank”
mixedbread.com

Note: Reranking is sold only inside Mixedbread Store queries, not as a standalone rerank endpoint; the FAQ gives $7.50 per thousand for semantic queries with reranking.

Status

GA

“mixedbread-ai/mxbai-rerank-v3.1-listwise · Listwise · Default.”
mixedbread.com
Context
Not stated
Documents per request
Not stated
Languages
Not stated
Open weights
Not stated

Note: No Hugging Face card was checked or linked for the listwise models; the docs present it as the hosted default.

Listwise reranker that reads the candidate set as a whole and follows natural-language instructions; default reranker for Store queries.

mxbai-rerank-large-v2

mixedbread-ai/mxbai-rerank-large-v2 - API and open weights - Add-on per 1K Store queries

GAinferred
Price (provider's unit)

+$3.50 per 1K queries (rerank add-on to $4 per 1K semantic Store queries)

“Semantic: Fine-grained semantic retrieval · $4 +$3.50 with rerank”
mixedbread.com

Note: Reranking is sold only inside Mixedbread Store queries, not as a standalone rerank endpoint; the FAQ gives $7.50 per thousand for semantic queries with reranking.

Status

GAinferred

“mixedbread-ai/mxbai-rerank-large-v2 · Pointwise · 1.5B-parameter model tuned for accuracy across 100+ languages.”
Status inferred from - mixedbread.com
Context
Not stated
Documents per request
Not stated
Languages

100+ languages

“multilingual support (100+ languages, outstanding English and Chinese performance)”
huggingface.co
Open weights

Yes - Apache 2.0, 1.54B parameters

mixedbread-ai/mxbai-rerank-large-v2 - license

“"license":"apache-2.0"”
huggingface.co
“"total":1543714304”
1,543,714,304 parameters - huggingface.co

Card lists "long-context support" without a token figure, so maxContext is null. Hosted by Mixedbread inside Store queries and selectable as a Together AI dedicated endpoint. The rendered card rounds size to "2B params"; the safetensors count is 1,543,714,304.

mxbai-rerank-base-v2

mixedbread-ai/mxbai-rerank-base-v2 - Open weights - Self-host (open weights or NIM containers)

GAinferred
Price (provider's unit)
Not stated

No per-call price: self-hosted.

Status

GAinferred

Status inferred: the source lists the model but does not label it.

Context
Not stated
Documents per request
Not stated
Languages

100+ languages

“multilingual support (100+ languages, outstanding English and Chinese performance)”
huggingface.co
Open weights

Yes - Apache 2.0, 494M parameters

mixedbread-ai/mxbai-rerank-base-v2 - license

“"license":"apache-2.0"”
huggingface.co
“"total":494032768”
494,032,768 parameters - huggingface.co

Card name: ProRank-0.5B. Not listed among hosted Store rerank models.

mxbai-rerank-large-v1

mixedbread-ai/mxbai-rerank-large-v1 - Open weights - Self-host (open weights or NIM containers)

GAinferred
Price (provider's unit)
Not stated

No per-call price: self-hosted.

Status

GAinferred

Status inferred: the source lists the model but does not label it.

Context
Not stated
Documents per request
Not stated
Languages

English

“"language":["en"]”
huggingface.co
Open weights

Yes - Apache 2.0, 435M parameters

mixedbread-ai/mxbai-rerank-large-v1 - license

“"license":"apache-2.0"”
huggingface.co
“"total":435062785”
435,062,785 parameters - huggingface.co

First-generation family (xsmall, base and large v1 exist on Hugging Face); only large-v1 is recorded here.

Older models

Earlier generations Mixedbread still serves or aliases to a newer model, kept apart from the current ones.

mxbai-rerank-v3-listwise

mixedbread-ai/mxbai-rerank-v3-listwise - API - No price stated

Older
Price (provider's unit)
Not stated

The provider's pages state no price for this model.

Status

Older

“No longer supported. Requests using this name are served by mixedbread-ai/mxbai-rerank-v3.1-listwise; use that model instead.”
mixedbread.com
Context
Not stated
Documents per request
Not stated
Languages
Not stated
Open weights
Not stated

Note: Not stated.

Name is aliased to v3.1-listwise.

FAQ

How much does Mixedbread reranking cost?

mxbai-rerank-v3.1-listwise: +$3.50 per 1K queries (rerank add-on to $4 per 1K semantic Store queries). mxbai-rerank-v3-listwise: not stated. mxbai-rerank-large-v2: +$3.50 per 1K queries (rerank add-on to $4 per 1K semantic Store queries). mxbai-rerank-base-v2: no per-call price (self-hosted). mxbai-rerank-large-v1: no per-call price (self-hosted). Prices are in Mixedbread's own units as of October 18, 2026.

What is the context length of Mixedbread rerankers?

Mixedbread's pages do not state a context length for these models.

Can I run Mixedbread rerankers myself?

Yes for mxbai-rerank-large-v2 (Apache 2.0), mxbai-rerank-base-v2 (Apache 2.0) and mxbai-rerank-large-v1 (Apache 2.0): the weights are on Hugging Face. The others are not published as open weights in the sources checked.

Sources

Last verified from each provider's own docs, pricing pages and Hugging Face cards; every quote was string-matched against the page that day. Prices are shown in the provider's own unit and change without notice, so check the linked source before you commit a budget.

Newsletter

Know when a reranker API changes

One email per week. New model releases, retrieval and pricing updates and what they mean for what you build.