Foundation Model · Amazon BedrockMistral FamilyFlagship TierMultimodal

Pixtral Large 25.02

Amazon Bedrock token pricing and cost optimization reference for Pixtral Large 25.02.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 7 AWS regions.

ProviderMistral AI

Maker HQParis, France

Class / TierFlagship

ModalityMultimodal

Prompt CachingSave 75%

Batch APISave 50%

AWS Regions7 Global

Bedrock Model IDmistral-ai.pixtral-large-25-02-v1:0

Input / Prompt

$2.00/ 1M tokens

$0.0020 per 1K tokens

Output / Completion

$6.00/ 1M tokens

$0.0060 per 1K tokens

Prompt Cache Read

$0.50/ 1M tokens

Save 75% vs prompt

Batch Inference

$1.00/ 1M in

Save 50% via Batch API

Price Ratio

1 : 3.0

Prompt to completion factor

Regional Reach

7AWS Regions

Compare 7 regions ↓

Alternatives to Pixtral Large 25.02

Option	Price vs Pixtral Large 25.02	Why look at it
Mistral Small Compare →	input-50%-$1.00/1M output-50%-$3.00/1M Standard tier, per 1M tokens	Next step down in price from Mistral AI (general tier)
Mistral Large Compare →	input+100%+$2.00/1M output+100%+$6.00/1M Standard tier, per 1M tokens	Next step up in price from Mistral AI
Mistral Large 2407 Compare →	inputsame price outputsame price Standard tier, per 1M tokens	Same Mistral line, different version
Devstral Compare →	input-80%-$1.60/1M output-67%-$4.00/1M Standard tier, per 1M tokens	Also from Mistral AI (general tier)

Pixtral Large 25.02 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: $2.00/1M · Output: $6.00/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Pixtral Large 25.02 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: $0.50 / 1M tokens
Write Rate (5m TTL): $2.50 / 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: $1.00 / 1M tokens
Batch Output: $3.00 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers7 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 7 available AWS cloud regions

Baseline: $2.00/1M in7 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)	$2.00	$6.00	—	—	Baseline
us-west-2 US West (Oregon)	$2.00	$6.00	—	—	Baseline
eu-central-1 EU (Frankfurt)	$2.00	$6.00	—	—	Baseline
eu-west-1 EU (Ireland)	$2.00	$6.00	—	—	Baseline
eu-west-3 EU (Paris)	$2.00	$6.00	—	—	Baseline
eu-north-1 EU (Stockholm)	$2.00	$6.00	—	—	Baseline
us-east-2 US East (Ohio)	$2.00	$6.00	—	—	Baseline

Developer Quickstart

Invoke Pixtral Large 25.02 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.pixtral-large-25-02-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Pixtral Large 25.02."}]
        }
    ],
    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")