Active modelProprietaryEmbedding2

Ctxdex Enterprise Embed 2

Agent MakersCtxdex Enterprise Embed

A second-generation embedding model in the Ctxdex Enterprise Embed family for embedding generation.

AcceptsTextProducesVectorReleasedAnnounced
View pricingPricing calculator

The calculator opens on this model; the scenario is yours to state.

Data captured as of

Overview

Intended useBest suited for embedding generation.
FamilyCtxdex Enterprise EmbedEnterprise embedding family.
AnnouncedAnnounced
DeprecatedNot applicableModel is current.
RetiredNot applicableModel is not retired.

What it does

Capabilities carry their support status; tasks are labels, because seven descriptions would bury the section.

Capabilities (0)

None recordedNo capability is recorded for this model.

Tasks (1)

Embedding Generation

Inputs & Outputs

Each modality is paired with the representation it is carried in, so a non-token model reads the same way a text one does.

Accepts

  • TextPlain Text

Produces

  • VectorEmbedding Vector

Technical Characteristics

A characteristic with no value states why it has none. An absence here is a recorded fact, not a gap in the page.

Embedding dimensions2048
Variable embedding dimensionsYes

Availability

Current offering available

Agent Makers

First Party Managed Api

Active offering
Effective from

Serving surfaces

Batch API · ActiveEmbedding API · Active

Astavra Enterprise AI

Enterprise Managed Ai

Active offering
Effective from

Serving surfaces

Embedding API · Active

Nimbrex Cloud

Cloud Managed Model

Active offering
Effective from

Serving surfaces

Embedding API · Active
Historical offeringsNone recorded
Downloadable distributionsNone recordedNo downloadable artefact has been published under these terms.

Serving Performance

Measured as of

Every figure is measured under the conditions beside it. Read without them, a latency number claims more than it can.

Measurement basis Synthetic ProfileMetrics 6
MetricTypical valueConditions
Workload Completion Latency MsCompletion latency for a named, fixed workload profile.150Ms
Capacity Mode: SHARED_ON_DEMANDDelivery Mode: BATCHProcessing Tier: STANDARDConcurrency Band: C1
Workload Completion Latency MsCompletion latency for a named, fixed workload profile.140Ms
Capacity Mode: SHARED_ON_DEMANDDelivery Mode: SYNCHRONOUSProcessing Tier: STANDARDConcurrency Band: C1
Workload Completion Latency MsCompletion latency for a named, fixed workload profile.150Ms
Capacity Mode: SHARED_ON_DEMANDDelivery Mode: SYNCHRONOUSProcessing Tier: STANDARDConcurrency Band: C1
Workload Units Per SecondThroughput in workload-profile-defined units per second.853.33Workload Unit Per Second
Capacity Mode: SHARED_ON_DEMANDDelivery Mode: BATCHProcessing Tier: STANDARDConcurrency Band: C1
Workload Units Per SecondThroughput in workload-profile-defined units per second.914.29Workload Unit Per Second
Capacity Mode: SHARED_ON_DEMANDDelivery Mode: SYNCHRONOUSProcessing Tier: STANDARDConcurrency Band: C1
Workload Units Per SecondThroughput in workload-profile-defined units per second.853.33Workload Unit Per Second
Capacity Mode: SHARED_ON_DEMANDDelivery Mode: SYNCHRONOUSProcessing Tier: STANDARDConcurrency Band: C1

Applicable Benchmarks

View all 44 in Benchmarks →

Benchmarks whose recorded requirements this model meets. Applicable means the requirements are met, not that the model was evaluated. No scores appear here.

44 applicable152 not recordedof 196 benchmark definitions
View all 44 in Benchmarks

Showing 3 of 18 families. Latest release per benchmark, up to 4 per family. Ordered by applicability, then name. Not a ranking.

152 not recorded. 141 have a required condition with no record for this model; 11 record no requirement at all. Nothing here says the model cannot meet them. View in Benchmarks

Resolved against the model baseline. A page that resolves a specific ModelSnapshot must re-resolve with that snapshot as the subject and say so.

Pricing Reference

Reference offering

Agent Makers · First Party Managed Api

Effective fromCaptured as of
MeterBasisRate
Embedding InputAudited embedding input-token rate$0.14 / 1000000Token

Full pricing for a single offering is one step further in, from this model’s pricing page, because it is addressed by offering and this page carries the model. The calculator opens on this model and prices a workload you state.

2 other current offerings are priced separately. This is the publisher's own offering, chosen as the reference — it is not the cheapest by definition. Rates are not comparable across offerings unless meter, unit and conditions match.

Derived chronology

Model Journey

Assembled from this model’s own lifecycle records, its snapshots, its providers’ offering and pricing history, and recorded succession. It is a view over those records, not a second source of truth, and undated lineage is deliberately not on it.

13 events3 scheduled ahead
  • Effective from
    PricingNormalUpcoming

    Agent Makers pricing scheduled

    Offering context: Agent Makers

    Scheduled to take effect on 2026-09-15. Not yet effective.

  • Effective from
    PricingNormalUpcoming

    Astavra Enterprise AI pricing scheduled

    Offering context: Astavra Enterprise AI

    Scheduled to take effect on 2026-09-15. Not yet effective.

  • Effective from
    PricingNormalUpcoming

    Nimbrex Cloud pricing scheduled

    Offering context: Nimbrex Cloud

    Scheduled to take effect on 2026-09-15. Not yet effective.

  • Effective from
    PricingNormal

    Agent Makers pricing became effective

    Offering context: Agent Makers

    Version current, effective from 2026-01-01.

  • Effective from
    PricingNormal

    Nimbrex Cloud pricing became effective

    Offering context: Nimbrex Cloud

    Version current, effective from 2026-01-01.

  • Effective from
    AvailabilityNormal

    Astavra Enterprise AI · Enterprise Managed Ai: Active

    Offering context: Astavra Enterprise AI

    Synthetic commercial activation.

Open full journey →

The first control expands this section in place, without filters or navigation. The second opens the standalone journey, which adds filtering on three axes, year grouping, per-event provenance and a shareable address.

Every date is the source record’s own effective date — a model lifecycle date, a snapshot release, an offering’s effective date, a pricing version’s effective-from. None of them is a load or capture timestamp.

Licence & Use Conditions

LicenceAgent Makers Proprietary Model Terms
Version1.0
SPDX identifierNot applicableSPDX identifies open-source licences; these are proprietary terms.
Legal textNo public URI recordedThe terms exist and are held internally; no public address has been published.Captured as of

Use conditions (0)

None recordedNo condition constrains use of this model beyond its licence.

Lifecycle & Lineage

Direct lineage

Successor Of

Ctxdex Enterprise Embed 1

Recommended replacement for

None recordedNo replacement recommendation is recorded in either direction.

Lifecycle history: Active on 2025-05-20.

Similar Industry Models

Captured as of

A positioning reference, not an equivalence claim. Each row states the axes it was drawn on, and covers only that part of this model's positioning.

Cohere Embed 4

Cohere

Provider documentation
DirectEnterprise EmbeddingDedicated Deployment

Differences recorded: Peer Multimodal.

Selected as a direct current reference for Ctxdex Enterprise Embed 2 based on enterprise embedding, dedicated deployment.

Checked 2026-09-14 · High confidence

Voyage 4 Large

Voyage AI

Provider documentation
ClosePremium Embedding

Selected as a close current reference for Ctxdex Enterprise Embed 2 based on premium embedding.

Checked 2026-09-14 · High confidence

Gemini Embedding 2

Google

Provider documentation
ReferenceMultimodal EmbeddingEnterprise Access

Differences recorded: Peer Multimodal.

Selected as a reference current reference for Ctxdex Enterprise Embed 2 based on multimodal embedding, enterprise access.

Checked 2026-09-14 · Medium confidence

Comparison method CTXDEX_COMPARABLES_V1.

Resolved from the ctxdex catalogue at build time. Every figure is a stored value or a derivation named in the read model; nothing on this page is computed in the browser.