Foundation Model · Amazon BedrockMistral FamilyLightweight TierAudio / SpeechMulti-Tier Pricing

Voxtral Mini 1.0

Amazon Bedrock token pricing and cost optimization reference for Voxtral Mini 1.0.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 13 AWS regions.

ProviderMistral AI

Maker HQParis, France

Class / TierLightweight

ModalityAudio / Speech

Prompt CachingSave 75%

Batch APISave 50%

AWS Regions13 Global

Bedrock Model IDmistral-ai.voxtral-mini-1-0-v1:0

Input / Prompt

$0.04/ 1M tokens

$0.0000 per 1K tokens

Output / Completion

$0.04/ 1M tokens

$0.0000 per 1K tokens

Prompt Cache Read

$0.01/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.02/ 1M in

Save 50% via Batch API

Price Ratio

1 : 1.0

Prompt to completion factor

Regional Reach

13AWS Regions

Compare 13 regions ↓

Alternatives to Voxtral Mini 1.0

Option	Price vs Voxtral Mini 1.0	Why look at it
Voxtral Small 1.0 Compare →	input+150%+$0.06/1M output+650%+$0.26/1M Standard tier, per 1M tokens	Next step up in price from Mistral AI (general tier)

Voxtral Mini 1.0 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: $0.04/1M · Output: $0.04/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Voxtral Mini 1.0 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: $0.01 / 1M tokens
Write Rate (5m TTL): $0.05 / 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: $0.02 / 1M tokens
Batch Output: $0.02 / 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

Regional Pricing Matrix

Live rates across all 13 available AWS cloud regions

Baseline: $0.04/1M inGovCloud: $0.06/1M 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)	$0.04	$0.04	—	$0.02	Baseline
us-west-2 US West (Oregon)	$0.04	$0.04	—	$0.02	Baseline
eu-central-1 EU (Frankfurt)	$0.05	$0.05	—	$0.02	+20% vs Baseline
eu-west-1 EU (Ireland)	$0.05	$0.05	—	$0.03	+25% vs Baseline
ap-northeast-1 Asia Pacific (Tokyo)	$0.05	$0.05	—	$0.03	+25% vs Baseline
ap-southeast-3 Asia Pacific (Jakarta)	$0.05	$0.05	—	$0.02	+20% vs Baseline
ap-south-1 Asia Pacific (Mumbai)	$0.05	$0.05	—	$0.03	+25% vs Baseline
ap-southeast-2 Asia Pacific (Sydney)	$0.04	$0.04	—	$0.02	+3% vs Baseline
eu-west-2 EU (London)	$0.06	$0.06	—	$0.03	+50% vs Baseline
eu-south-1 EU (Milan)	$0.05	$0.05	—	$0.03	+25% vs Baseline
eu-north-1 EU (Stockholm)	$0.05	$0.05	—	$0.02	+20% vs Baseline
sa-east-1 South America (Sao Paulo)	$0.05	$0.05	—	$0.03	+25% vs Baseline
us-east-2 US East (Ohio)	$0.04	$0.04	—	$0.02	Baseline

Developer Quickstart

Invoke Voxtral Mini 1.0 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="mistral-ai.voxtral-mini-1-0-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Voxtral Mini 1.0."}]
        }
    ],
    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")