Llama 2 Chat 70B Pricing & Token Calculator (Meta)

Input / Prompt

$1.95/ 1M tokens

$0.0019 per 1K tokens

Output / Completion

$2.56/ 1M tokens

$0.0026 per 1K tokens

Prompt Cache Read

$0.49/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.97/ 1M in

Save 50% via Batch API

Price Ratio

1 : 1.3

Prompt to completion factor

Regional Reach

2AWS Regions

Compare 2 regions ↓

Alternatives to Llama 2 Chat 70B

Option	Price vs Llama 2 Chat 70B	Why look at it
Llama 2 Chat 13B Compare →	input-62%-$1.20/1M output-61%-$1.56/1M Standard tier, per 1M tokens	Next step down in price from Meta (lightweight tier)

Llama 2 Chat 70B 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: $1.95/1M · Output: $2.56/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Llama 2 Chat 70B 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: $0.49 / 1M tokens
Write Rate (5m TTL): $2.44 / 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: $0.97 / 1M tokens
Batch Output: $1.28 / 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: $1.95/1M 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)	$1.95	$2.56	—	—	Baseline
us-west-2 US West (Oregon)	$1.95	$2.56	—	—	Baseline

Developer Quickstart

Invoke Llama 2 Chat 70B 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="meta.llama-2-chat-70b-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Llama 2 Chat 70B."}]
        }
    ],
    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")

Compare Llama 2 Chat 70B with Alternatives

Open Multi-Model Estimator →

Llama 2 Chat 70B vsCommandCohere

Input Rate:$1.00/1M

Output Rate:$2.00/1M

Compare Side-by-Side →

Llama 2 Chat 70B vsCommand LightCohere

Input Rate:$0.30/1M

Output Rate:$0.60/1M