Foundation Model · Amazon BedrockGPT FamilyGeneral TierTextMulti-Tier Pricing

gpt-oss-120b

Amazon Bedrock token pricing and cost optimization reference for gpt-oss-120b.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 15 AWS regions.

ProviderOpenAI

Maker HQSan Francisco, California, USA

Class / TierGeneral

ModalityText

Prompt CachingSave 75%

Batch APISave 50%

AWS Regions15 Global

Bedrock Model IDopenai.gpt-oss-120b-v1:0

Input / Prompt

$0.15/ 1M tokens

$0.0001 per 1K tokens

Output / Completion

$0.60/ 1M tokens

$0.0006 per 1K tokens

Prompt Cache Read

$0.04/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.07/ 1M in

Save 50% via Batch API

Price Ratio

1 : 4.0

Prompt to completion factor

Regional Reach

15AWS Regions

Compare 15 regions ↓

On Google Cloud Vertex AI

The same model is sold through Vertex AI at one global rate per price type. These are Google's published rates, not the AWS rates above; both hosts are shown because the model is sold on both.

Rate	Vertex AI, USD per 1M tokens
Input	$0.09
Output	$0.36
Cache read	—
Batch input	$0.04
Batch output	$0.18
Input, long context	—
Output, long context	—
Output, thinking	—

Vertex AI rates are global: Google publishes one rate covering every region where the model runs, against the per-region AWS prices above. A dash means Google publishes no rate for that price type.

Alternatives to gpt-oss-120b

Option	Price vs gpt-oss-120b	Why look at it
gpt-oss-20b Compare →	input-53%-$0.08/1M output-50%-$0.30/1M Standard tier, per 1M tokens	Next step down in price from OpenAI
GPT-5.6-LUNA Compare →	input+76%+$0.114/1M output+164%+$0.984/1M Standard tier, per 1M tokens	Next step up in price from OpenAI (flagship tier)
GPT OSS Safeguard 120B Compare →	inputsame price outputsame price Standard tier, per 1M tokens	Same GPT line, different version
GPT OSS Safeguard 20B Compare →	input-53%-$0.08/1M output-67%-$0.40/1M Standard tier, per 1M tokens	Also from OpenAI

gpt-oss-120b 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)%

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: $0.15/1M · Output: $0.60/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with gpt-oss-120b 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: $0.04 / 1M tokens
Write Rate (5m TTL): $0.19 / 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: $0.07 / 1M tokens
Batch Output: $0.30 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers15 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

Rates by region

Live rates across all 15 available AWS cloud regions

Baseline: $0.15/1M inGovCloud: $0.23/1M in15 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)	$0.15	$0.60	—	$0.07	Baseline
us-west-2 US West (Oregon)	$0.15	$0.60	—	$0.07	Baseline
eu-central-1 EU (Frankfurt)	$0.20	$0.79	—	$0.10	+33% vs Baseline
eu-west-1 EU (Ireland)	$0.18	$0.70	—	$0.09	+20% vs Baseline
ap-northeast-1 Asia Pacific (Tokyo)	$0.18	$0.73	—	$0.09	+20% vs Baseline
us-gov-west-1 AWS GovCloud (US-West)	$0.18	$0.72	—	$0.09	GovCloud (+20%)
ap-southeast-3 Asia Pacific (Jakarta)	$0.16	$0.62	—	$0.08	+7% vs Baseline
ap-south-1 Asia Pacific (Mumbai)	$0.18	$0.71	—	$0.09	+20% vs Baseline
ap-southeast-2 Asia Pacific (Sydney)	$0.15	$0.62	—	$0.08	+3% vs Baseline
us-gov-east-1 AWS GovCloud (US-East)	$0.18	$0.72	—	$0.09	GovCloud (+20%)
eu-west-2 EU (London)	$0.23	$0.93	—	$0.12	+53% vs Baseline
eu-south-1 EU (Milan)	$0.20	$0.79	—	$0.10	+33% vs Baseline
eu-north-1 EU (Stockholm)	$0.15	$0.60	—	$0.07	Baseline
sa-east-1 South America (Sao Paulo)	$0.18	$0.73	—	$0.09	+20% vs Baseline
us-east-2 US East (Ohio)	$0.15	$0.60	—	$0.07	Baseline

Developer Quickstart

Invoke gpt-oss-120b 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-oss-120b-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of gpt-oss-120b."}]
        }
    ],
    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")