Kimi K3 Pricing & Token Calculator (Moonshot AI)

Input / Prompt

$3.00/ 1M tokens

$0.0030 per 1K tokens

Output / Completion

$15.00/ 1M tokens

$0.0150 per 1K tokens

Prompt Cache Read

$0.15/ 1M tokens

Save 95% vs prompt

Batch Inference

$1.65/ 1M in

Save 45% via Batch API

Price Ratio

1 : 5.0

Prompt to completion factor

Regional Reach

36AWS Regions

Compare 36 regions ↓

Alternatives to Kimi K3

Option	Price vs Kimi K3	Why look at it
Kimi K2.5 Compare →	input-80%-$2.40/1M output-80%-$12.00/1M Standard tier, per 1M tokens	Next step down in price from Moonshot AI
Kimi K2 Thinking Compare →	input-80%-$2.40/1M output-83%-$12.50/1M Standard tier, per 1M tokens	Same General line, different version

Kimi K3 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 S3

Estimated Monthly Spend

$0.00

Fresh Prompts:$0.00

Cached Prompts:$0.00

Completions:$0.00

Active: Input: $3.00/1M · Output: $15.00/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Kimi K3 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: $0.15 / 1M tokens
Write Rate (5m TTL): $1.88 / 1M tokens
Ideal for: Multi-turn conversations, RAG document queries, structured schemas

Batch InferenceSave 45%

Asynchronous bulk processing submitted via Amazon S3 with a standard 24-hour turnaround SLA.

Batch Input: $1.65 / 1M tokens
Batch Output: $8.25 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers36 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 36 available AWS cloud regions

Baseline: $3.00/1M inGovCloud: $3.60/1M in36 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)	$3.00	$15.00	$0.30	$1.65	Baseline
us-west-2 US West (Oregon)	$3.00	$15.00	$0.30	$1.65	Baseline
eu-central-1 EU (Frankfurt)	$3.00	$15.00	$0.30	$1.65	Baseline
eu-west-1 EU (Ireland)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-northeast-1 Asia Pacific (Tokyo)	$3.00	$15.00	$0.30	$1.65	Baseline
us-gov-west-1 AWS GovCloud (US-West)	$3.60	$18.00	$0.36	$1.98	GovCloud (+20%)
af-south-1 Africa (Cape Town)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-east-1 Asia Pacific (Hong Kong)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-south-2 Asia Pacific (Hyderabad)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-southeast-3 Asia Pacific (Jakarta)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-southeast-5 Asia Pacific (Malaysia)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-southeast-4 Asia Pacific (Melbourne)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-south-1 Asia Pacific (Mumbai)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-southeast-6 Asia Pacific (New Zealand)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-northeast-3 Asia Pacific (Osaka)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-northeast-2 Asia Pacific (Seoul)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-southeast-1 Asia Pacific (Singapore)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-southeast-2 Asia Pacific (Sydney)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-east-2 Asia Pacific (Taipei)	$3.00	$15.00	$0.30	$1.65	Baseline
ap-southeast-7 Asia Pacific (Thailand)	$3.00	$15.00	$0.30	$1.65	Baseline
us-gov-east-1 AWS GovCloud (US-East)	$3.60	$18.00	$0.36	$1.98	GovCloud (+20%)
ca-central-1 Canada (Central)	$3.00	$15.00	$0.30	$1.65	Baseline
ca-west-1 Canada West (Calgary)	$3.00	$15.00	$0.30	$1.65	Baseline
eu-west-2 EU (London)	$3.00	$15.00	$0.30	$1.65	Baseline
eu-south-1 EU (Milan)	$3.00	$15.00	$0.30	$1.65	Baseline
eu-west-3 EU (Paris)	$3.00	$15.00	$0.30	$1.65	Baseline
eu-north-1 EU (Stockholm)	$3.00	$15.00	$0.30	$1.65	Baseline
eu-south-2 Europe (Spain)	$3.00	$15.00	$0.30	$1.65	Baseline
eu-central-2 Europe (Zurich)	$3.00	$15.00	$0.30	$1.65	Baseline
il-central-1 Israel (Tel Aviv)	$3.00	$15.00	$0.30	$1.65	Baseline
mx-central-1 Mexico (Central)	$3.00	$15.00	$0.30	$1.65	Baseline
me-south-1 Middle East (Bahrain)	$3.00	$15.00	$0.30	$1.65	Baseline
me-central-1 Middle East (UAE)	$3.00	$15.00	$0.30	$1.65	Baseline
sa-east-1 South America (Sao Paulo)	$3.00	$15.00	$0.30	$1.65	Baseline
us-east-2 US East (Ohio)	$3.00	$15.00	$0.30	$1.65	Baseline
us-west-1 US West (N. California)	$3.00	$15.00	$0.30	$1.65	Baseline

Developer Quickstart

Invoke Kimi K3 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="moonshot-ai.kimi-k3-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Kimi K3."}]
        }
    ],
    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")