Skip to content
Model infoModelsSnapshot: 15 Oct 2026

AI21 Labs / Task-specific services

Text Improvements

Historical managed text-editing service that suggests changes for fluency, vocabulary and clarity, with edit locations in the original passage.

Text analysis
historicalClosed-source managed componentText analysisRewriting
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
7 of 21 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedAI21 Studio (historical managed service)
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

No exact-version evidence collected; specifications of another model are not inherited.

Maximum input tokens
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Maximum output
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
Text suggestionsSource for Output modalities (opens in a new tab)
Reasoning
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Tool calling
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Structured output
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Streaming
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Batch processing
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Fine-tuning
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Context caching
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Knowledge cutoff
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Release date
2023-03-09Source for Release date (opens in a new tab)

Original task-API announcement.

Parameters
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Architecture
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Languages
Not collected

No exact-version evidence collected; specifications of another model are not inherited.

Release identity
Managed task service; independent weight identity unverifiedSource for Release identity (opens in a new tab)
API request fields
text and a non-empty types listSource for API request fields (opens in a new tab)
Generation controls
fluency, vocabulary/specificity, vocabulary/variety, clarity/short-sentences, clarity/concisenessSource for Generation controls (opens in a new tab)

Requested edit categories from the historical SDK enum, not separate models.

Response metadata
Response ID and improvements with suggestions, start/end index, original text and improvement type.Source for Response metadata (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.

AI21 Studio (historical managed service)

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

Service route is documented, but no separately selectable checkpoint ID is provided.

Access
Historical SDK POST route: /improvements relative to the configured Studio API base URL. No separate selectable model ID or current availability established.
Regions
Not collected

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.

AI21 Studio (historical managed service)

Not verified

No version-specific cache contract verified.

How it works
Not collected

No version-specific cache contract verified.

Minimum reusable input
Not collected

No version-specific cache contract verified.

Lifetime & refresh
Not collected

No version-specific cache contract verified.

How to enable it
Not collected

No version-specific cache contract verified.

Usage fields
Not collected

No version-specific cache contract verified.

Billing rules
Not collected

No version-specific cache contract verified.

Limits & data boundaries
Not collected

No version-specific cache contract verified.

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-operated task API documented in the original launch and official SDK. This record describes the managed component; an independent proprietary checkpoint identity is not established.

Classification evidence (opens in a new tab)

Sources reviewed