LLM ReferenceLLM Reference
AWS Bedrock

Jurassic-2 Ultra on AWS Bedrock

Jurassic-2 · AI21 Labs

Serverless

Last refreshed 2026-05-11. Next refresh: weekly.

Why use Jurassic-2 Ultra on AWS Bedrock?

AWS Bedrock offers Jurassic-2 Ultra with pay-as-you-go pricing at $18.80/1M input tokens. AWS Bedrock is Amazon's fully managed foundation-model service, providing unified API access to top models from Anthropic, Meta, Mistral, and other leading AI labs with built-in tools for RAG, fine-tuning, and AI agent development.

Compare Jurassic-2 Ultra across 2 providers to find the best fit for your use case
Input / 1M
$18.80
Output / 1M
$18.80
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install boto3
Auth
export AWS_ACCESS_KEY_ID=...
Call
import boto3
client = boto3.client("bedrock-runtime", region_name="us-east-1")
response = client.converse(
    modelId="jurassic-2-ultra",
Model ID
jurassic-2-ultra

Request example

import boto3

# Reads AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION from env
client = boto3.client("bedrock-runtime", region_name="us-east-1")
response = client.converse(
    modelId="jurassic-2-ultra",
    messages=[{
        "role": "user",
        "content": [{"text": "Hello"}]
    }]
)
print(response["output"]["message"]["content"][0]["text"])

Gotchas

  • Use Amazon Bedrock model IDs, e.g. "anthropic.claude-3-opus-20240229-v1:0" for on-demand, or cross-region inference profile IDs like "us.anthropic.claude-opus-4-7-20251101-v1:0". These differ from the public model slug.
  • The endpoint template includes a region segment; set the same region in your SDK/client configuration.
  • The examples expect AWS_ACCESS_KEY_ID; rename it only if your application config maps the new variable.

Compare Jurassic-2 Ultra Across Providers

ProviderInput (per 1M)Output (per 1M)
AWS Bedrock$18.80$18.80
AI21 Studio$18.80$18.80

Pricing

TypePrice (per 1M)
Input tokens$18.80
Output tokens$18.80

Capabilities

Structured Outputs

About Jurassic-2 Ultra

Jurassic-2 Ultra by AI21 Labs is their most advanced large language model, designed for intricate text generation tasks that demand high-quality output. It is specifically optimized for "zero-shot" prompts, meaning it performs well without requiring example inputs—making it perfect for chatbot and conversational applications. As the flagship model in the Jurassic series, it features over 60 billion parameters and supports multiple languages such as English, Spanish, and French. While its primary strengths are in text completion, generation, and summarization, it also excels in tasks like question answering and advanced information extraction. Trained on a vast array of texts, including curated CommonCrawl and Wikipedia data, it was exposed to about 1.2 trillion tokens. However, users should be mindful of potential inaccuracies, biases, and its July 2022 knowledge cutoff. Despite these considerations, Jurassic-2 Ultra is widely used in various applications, including AI21’s Wordtune, to enhance reading and writing experiences.

FAQ

What does Jurassic-2 Ultra cost on AWS Bedrock?

On AWS Bedrock, Jurassic-2 Ultra costs $18.8 per 1M input tokens and $18.8 per 1M output tokens.

How does AWS Bedrock compare to other Jurassic-2 Ultra providers?

Jurassic-2 Ultra is available from 2 providers. The cheapest input pricing is $18.8/1M tokens from AWS Bedrock.

Who created Jurassic-2 Ultra?

Jurassic-2 Ultra was created by AI21 Labs as part of the Jurassic-2 model family.

Is Jurassic-2 Ultra open source?

Jurassic-2 Ultra's open source status is unknown in the seed data.

Get Started

Model Specs

Released2023-03-09
Parameters60B
ArchitectureDecoder Only

Provider

AWS Bedrock
AWS Bedrock

Amazon Web Services

All models on AWS Bedrock