Skip to content
Model infoModelsSnapshot: 15 Oct 2026

AI21 Labs / Jurassic-2

Jurassic-2 Light

Compact instruction-following language model for text generation and classification.

Language models (LLMs)
availableClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
7 of 18 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedAmazon SageMaker JumpStart
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
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)

The reviewed SageMaker JumpStart offering is not fine-tunable; this is not a claim about every historical AI21 service.

Knowledge cutoff
Mid-2022Source for Knowledge cutoff (opens in a new tab)

Original release training-data statement; later hosted revisions are not specified.

Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
English, Spanish, French, German, Portuguese, Italian, DutchSource for Languages (opens in a new tab)
Context caching
Not collected
API aliases
ai21-jurassic-2-lightSource for API aliases (opens in a new tab)

SageMaker catalog ID; inference uses the endpoint name chosen during deployment.

Release identity
Instruction-following offering from the simplified Light / Mid / Ultra lineupSource for Release identity (opens in a new tab)

Original Jurassic-2 Large base model is recorded separately. Instruction-tuned Grande/Jumbo names belong to the existing Mid/Ultra family records and are not added again.

Access & pricing

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

Amazon SageMaker JumpStart

Provider source (opens in a new tab)
API model ID
ai21-jurassic-2-light
Access
Subscribe to the model’s AWS Marketplace offer and deploy a SageMaker endpoint. Catalog ID is not the user-chosen inference endpoint name. Charges depend on the offer and instance configuration; no current numeric rate was verified.
Regions
Not collected
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)
Inference instance types
ml.g4dn.12xlarge, ml.g5.12xlarge, ml.g5.48xlarge, ml.p4d.24xlargeSource for Inference instance types (opens in a new tab)
Billing basis
Usage time and instance type; check the exact Marketplace offer for software and infrastructure charges.Source for Billing basis (opens in a new tab)

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.

Amazon SageMaker JumpStart

ai21-jurassic-2-light
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

Named in AWS’s proprietary model inventory; its accompanying deployment guide states that weights are inaccessible. No corresponding public checkpoint was found in AI21’s official model repository.

Classification evidence (opens in a new tab)

Sources reviewed