Skip to content
Model infoModelsSnapshot: 15 Oct 2026

IBM / Slate

Slate 30M English Base

IBM’s encoder-only base model used to initialize its proprietary retrieval model.

Text analysis
historicalClosed weightsText analysis
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
4 of 16 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedIBM Slate base reference
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
Not collected
Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
30MSource for Parameters (opens in a new tab)
Architecture
Small RoBERTa encoder, 6 layers; distilled from Slate 125MSource for Architecture (opens in a new tab)
Languages
EnglishSource for Languages (opens in a new tab)
Context caching
Not collected

Access & pricing

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

IBM Slate base reference

Provider source (opens in a new tab)
API model ID
Not collected

Research/base checkpoint or historical revision; a separately callable selector has not been verified.

Access
Base encoder named in the retrieval model card; no standalone API selector verified.
Regions
Product, deployment, and region restrictions apply. This record does not imply global availability or residency.

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

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

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.

IBM Slate base reference

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

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

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

IBM documents its internal Slate encoder base, formerly WatBERT for the 125M model. Closed-weight classification is inferred for this exact proprietary checkpoint; public Granite Embedding successors are different releases. A standalone public weight artifact or public base-model endpoint was not verified.

Classification evidence (opens in a new tab)

Sources reviewed