Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Aleph Alpha / Luminous Explore

Luminous Explore Query

Luminous Explore Query is a trained semantic representation from the Luminous Explore family, routed through luminous-base with representation=asymmetric_query.

historicalClosed weightsEmbeddings
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
11 of 21 specification fields collected
Input token limit2K2,048 tokens
Vector dimensions128 with compression; full default dimension not established here.See specification notes below
Input billingNot collectedAleph Alpha API (historical documentation)
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
2,048 tokensSource for Context / input limit (opens in a new tab)

Underlying luminous-base route in a 6 August 2025 recording; current deployment may differ.

Maximum output
0 tokensSource for Maximum output (opens in a new tab)

Embedding output, not generated text.

Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
SupportedSource for Batch processing (opens in a new tab)

Synchronous /batch_semantic_embed is recorded for luminous-base; no asynchronous Batch API, discount or account quota is implied.

Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected

Announcement dates and SDK selector suffixes do not establish exact checkpoint release dates.

Parameters
13,000,000,000Source for Parameters (opens in a new tab)

Published size of the Luminous-Base-derived Explore family.

Languages
Not collected
Context caching
Not collected

SDK caches tokenizers and model metadata locally; this does not establish prompt-cache support or discounted cached input.

Output modalities
Embedding vectorSource for Output modalities (opens in a new tab)
Usage metering
Not collected

No current official model-specific rate verified. Historical third-party dollar estimates are not treated as provider prices.

Endpoint availability
Historically documented model or representation. Current account-specific availability not verified.Source for Endpoint availability (opens in a new tab)
Architecture
SGPT-style fine-tuning of Luminous Base for semantic representations.Source for Architecture (opens in a new tab)
Embedding dimensions
128 with compression; full default dimension not established here.Source for Embedding dimensions (opens in a new tab)

Recorded representation list includes 128-dimensional symmetric/query/document modes; default dimension is not inferred.

Native model options
model=luminous-base; representation=asymmetric_querySource for Native model options (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Aleph Alpha API (historical documentation)

Provider source (opens in a new tab)
API model ID
luminous-base

Use representation=asymmetric_query; not a separate native model ID.

Access
Historical /semantic_embed route with model=luminous-base and representation=asymmetric_query.
Regions
No model-specific current processing region verified

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Current retention and training-use commitments not established for this historical model record.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Aleph Alpha API (historical documentation)

luminous-base
Not verified

No provider-documented prompt cache verified for this exact model.

How it works
Not collected

Local SDK tokenizer/context-size memoization is not provider prompt caching.

Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected

No cached-input rate verified.

Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Provider documents this Luminous model as a hosted commercial model or research demonstration. No original Luminous weight release was found in reviewed official model/repository listings. This is a qualified review finding; public SDK code and other open-weight Aleph Alpha families do not release these weights.

Classification evidence (opens in a new tab)

Lifecycle dates

Explore announced23 Sept 2022Source (opens in a new tab)

Sources reviewed