Foundation Model · Amazon BedrockQwen FamilyGeneral TierTextMulti-Tier Pricing

Qwen3 235B A22B 2507

By Alibaba (Qwen) →⚖️ Compare Model →

Amazon Bedrock token pricing and cost optimization reference for Qwen3 235B A22B 2507.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 13 AWS regions.

ProviderAlibaba (Qwen)

Maker HQHangzhou, Zhejiang, China

Class / TierGeneral

ModalityText

Prompt CachingSave 75%

Batch APISave 50%

AWS Regions13 Global

Bedrock Model IDalibaba.qwen3-235b-a22b-2507-v1:0

Input / Prompt

$0.22/ 1M tokens

$0.0002 per 1K tokens

Output / Completion

$0.88/ 1M tokens

$0.0009 per 1K tokens

Prompt Cache Read

$0.06/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.11/ 1M in

Save 50% via Batch API

Price Ratio

1 : 4.0

Prompt to completion factor

Regional Reach

13AWS Regions

Compare 13 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	$0.22
Output	$0.88
Cache read	—
Batch input	$0.11
Batch output	$0.44
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 Qwen3 235B A22B 2507

Option	Price vs Qwen3 235B A22B 2507	Why look at it
Qwen3 Coder 30B A3B Compare →	input-32%-$0.07/1M output-32%-$0.28/1M Standard tier, per 1M tokens	Next step down in price from Alibaba (Qwen) (lightweight tier)
Qwen3 Next 80B A3B Compare →	input-36%-$0.08/1M output+36%+$0.32/1M Standard tier, per 1M tokens	Next step up in price from Alibaba (Qwen) (lightweight tier)
Qwen3 Coder Next Compare →	input+127%+$0.28/1M output+36%+$0.32/1M Standard tier, per 1M tokens	Same Qwen line, different version (reasoning tier)
Qwen3 Coder 480B A35B Compare →	input+105%+$0.23/1M output+105%+$0.92/1M Standard tier, per 1M tokens	Also from Alibaba (Qwen) (reasoning tier)

Qwen3 235B A22B 2507 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: $0.22/1M · Output: $0.88/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Qwen3 235B A22B 2507 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: $0.06 / 1M tokens
Write Rate (5m TTL): $0.28 / 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: $0.11 / 1M tokens
Batch Output: $0.44 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers13 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 13 available AWS cloud regions

Baseline: $0.22/1M inGovCloud: $0.34/1M in13 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)	$0.22	$0.88	—	$0.11	Baseline
us-west-2 US West (Oregon)	$0.22	$0.88	—	$0.11	Baseline
eu-central-1 EU (Frankfurt)	$0.29	$1.16	—	$0.15	+32% vs Baseline
eu-west-1 EU (Ireland)	$0.26	$1.06	—	$0.13	+20% vs Baseline
ap-northeast-1 Asia Pacific (Tokyo)	$0.27	$1.06	—	$0.14	+23% vs Baseline
ap-southeast-3 Asia Pacific (Jakarta)	$0.23	$0.91	—	$0.11	+5% vs Baseline
ap-south-1 Asia Pacific (Mumbai)	$0.26	$1.04	—	$0.13	+18% vs Baseline
ap-southeast-2 Asia Pacific (Sydney)	$0.23	$0.91	—	$0.11	+3% vs Baseline
eu-west-2 EU (London)	$0.34	$1.37	—	$0.17	+55% vs Baseline
eu-south-1 EU (Milan)	$0.29	$1.16	—	$0.14	+32% vs Baseline
eu-north-1 EU (Stockholm)	$0.22	$0.88	—	$0.11	Baseline
sa-east-1 South America (Sao Paulo)	$0.26	$1.06	—	$0.13	+20% vs Baseline
us-east-2 US East (Ohio)	$0.22	$0.88	—	$0.11	Baseline

Developer Quickstart

Invoke Qwen3 235B A22B 2507 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="alibaba.qwen3-235b-a22b-2507-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Qwen3 235B A22B 2507."}]
        }
    ],
    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")