Foundation Model · Amazon BedrockJurassic FamilyFlagship TierText

Jurassic-2 Ultra

Amazon Bedrock token pricing and cost optimization reference for Jurassic-2 Ultra.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 2 AWS regions.

ProviderAI21 Labs

Maker HQTel Aviv, Israel

Class / TierFlagship

ModalityText

Prompt CachingSave 75%

Batch APISave 50%

AWS Regions2 Global

Bedrock Model IDai21-labs.jurassic-2-ultra-v1:0

Input / Prompt

$18.80/ 1M tokens

$0.0188 per 1K tokens

Output / Completion

$18.80/ 1M tokens

$0.0188 per 1K tokens

Prompt Cache Read

$4.70/ 1M tokens

Save 75% vs prompt

Batch Inference

$9.40/ 1M in

Save 50% via Batch API

Price Ratio

1 : 1.0

Prompt to completion factor

Regional Reach

2AWS Regions

Compare 2 regions ↓

Alternatives to Jurassic-2 Ultra

Option	Price vs Jurassic-2 Ultra	Why look at it
Jurassic-2 Mid Compare →	input-34%-$6.30/1M output-34%-$6.30/1M Standard tier, per 1M tokens	Next step down in price from AI21 Labs (balanced tier)
Jamba 1.5 Large Compare →	input-89%-$16.80/1M output-57%-$10.80/1M Standard tier, per 1M tokens	Also from AI21 Labs
Jamba-Instruct Compare →	input-97%-$18.30/1M output-96%-$18.10/1M Standard tier, per 1M tokens	Also from AI21 Labs (general tier)
Jamba 1.5 Mini Compare →	input-99%-$18.60/1M output-98%-$18.40/1M Standard tier, per 1M tokens	Also from AI21 Labs (lightweight tier)

Jurassic-2 Ultra Spend Estimator

Model inference spend by prompt volume, cache hit rate, and batch processing.

Prompt Tokens (Millions / month)

M tokens

Completion Tokens (Millions / month)

M tokens

Prompt Cache Hit Rate(75% discount on cached context)

30%

Batch API Mode50% discount on non-realtime async jobs via S3

Estimated Monthly Spend

$0.00

Fresh Prompts:$0.00

Cached Prompts:$0.00

Completions:$0.00

Active: Input: $18.80/1M · Output: $18.80/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Jurassic-2 Ultra on AWS

Prompt CachingSave ~75%

Caches repetitive system instructions, schemas, and document prefixes in memory with 5-minute and extended 1-hour TTL tiers.

Read Rate: $4.70 / 1M tokens
Write Rate (5m TTL): $23.50 / 1M tokens
Ideal for: Multi-turn conversations, RAG document queries, structured schemas

Batch InferenceSave 50%

Asynchronous bulk processing submitted via Amazon S3 with a standard 24-hour turnaround SLA.

Batch Input: $9.40 / 1M tokens
Batch Output: $9.40 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers2 Regions

AWS Bedrock supports standard on-demand inference, priority reserved throughput, and cross-region routing.

Standard: Lowest latency, pay-per-token with zero commitments
Cross-Region Routing: Automatically burst traffic to available regional capacity
GovCloud: Dedicated isolated compliance partitions with +20% uplift

Regional Pricing Matrix

Live rates across all 2 available AWS cloud regions

Baseline: $18.80/1M in2 Global Regions

AWS Region	Prompt Input $/1M	Completion Output $/1M	Cache Read $/1M	Batch Input $/1M	Pricing Tier
us-east-1 US East (N. Virginia)	$18.80	$18.80	—	—	Baseline
us-west-2 US West (Oregon)	$18.80	$18.80	—	—	Baseline

Developer Quickstart

Invoke Jurassic-2 Ultra via Amazon Bedrock Converse API

Python (boto3) · Amazon Bedrock Runtime

import boto3

# Amazon Bedrock Converse API invocation
client = boto3.client("bedrock-runtime", region_name="us-east-1")

response = client.converse(
    modelId="ai21-labs.jurassic-2-ultra-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Jurassic-2 Ultra."}]
        }
    ],
    inferenceConfig={
        "maxTokens": 1024,
        "temperature": 0.7
    }
)

output_text = response["output"]["message"]["content"][0]["text"]
usage = response["usage"]
print(f"Response: {output_text}")
print(f"Usage: {usage['inputTokens']} in, {usage['outputTokens']} out")