GPT-5.6-LUNA Pricing & Token Calculator (OpenAI)

Input / Prompt

$0.26/ 1M tokens

$0.0003 per 1K tokens

Output / Completion

$1.58/ 1M tokens

$0.0016 per 1K tokens

Prompt Cache Read

$0.01/ 1M tokens

Save 95% vs prompt

Batch Inference

$0.13/ 1M in

Save 50% via Batch API

Price Ratio

1 : 6.0

Prompt to completion factor

Regional Reach

1AWS Regions

Compare 1 regions ↓

Alternatives to GPT-5.6-LUNA

Option	Price vs GPT-5.6-LUNA	Why look at it
gpt-oss-120b Compare →	input-43%-$0.114/1M output-62%-$0.984/1M Standard tier, per 1M tokens	Next step down in price from OpenAI (general tier)
GPT-5.6-TERRA Compare →	input+900%+$2.38/1M output+900%+$14.26/1M Standard tier, per 1M tokens	Next step up in price from OpenAI
gpt-oss-20b Compare →	input-73%-$0.194/1M output-81%-$1.28/1M Standard tier, per 1M tokens	Same GPT line, different version (general tier)
GPT OSS Safeguard 20B Compare →	input-73%-$0.194/1M output-87%-$1.38/1M Standard tier, per 1M tokens	Also from OpenAI (general tier)

GPT-5.6-LUNA 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(95% discount on cached context)

30%

Batch API Mode50% discount on non-realtime async jobs via S3Long Context (>200k)Tiered pricing for >200,000 prompt tokens

Estimated Monthly Spend

$0.00

Fresh Prompts:$0.00

Cached Prompts:$0.00

Completions:$0.00

Active: Input: $0.26/1M · Output: $1.58/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with GPT-5.6-LUNA on AWS

Prompt CachingSave ~95%

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

Read Rate: $0.01 / 1M tokens
Write Rate (5m TTL): $0.17 / 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: $0.13 / 1M tokens
Batch Output: $0.79 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Long Context (>200k)High-Capacity Tier

Dedicated high-memory execution for enterprise documents and large context windows exceeding 200,000 tokens.

Long Context Input: $0.26 / 1M tokens
Long Context Output: $1.19 / 1M tokens
Ideal for: Full codebase ingest, multi-book synthesis, large video transcripts

Regional Pricing Matrix

Live rates across all 1 available AWS cloud regions

Baseline: $0.26/1M in1 Global Regions

AWS Region	Prompt Input $/1M	Completion Output $/1M	Cache Read $/1M	Batch Input $/1M	Pricing Tier
us-gov-west-1 AWS GovCloud (US-West)	$0.26	$1.58	$0.03	$0.13	GovCloud

Developer Quickstart

Invoke GPT-5.6-LUNA 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="openai.gpt-5-6-luna-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of GPT-5.6-LUNA."}]
        }
    ],
    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")