Kimi K2 Thinking
Amazon Bedrock token pricing and cost optimization reference for Kimi K2 Thinking.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 13 AWS regions.
moonshot-ai.kimi-k2-thinking-v1:0On 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 | $0.60 |
| Output | $2.50 |
| Cache read | $0.06 |
| Batch input | — |
| Batch output | — |
| 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 Kimi K2 Thinking
Kimi K2 Thinking Spend Estimator
Model inference spend by prompt volume, cache hit rate, and batch processing.
Key Cost Levers & Architecture
Practical mechanisms to reduce inference costs with Kimi K2 Thinking on AWSCaches 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): $0.75 / 1M tokens
- Ideal for: Multi-turn conversations, RAG document queries, structured schemas
Asynchronous bulk processing submitted via Amazon S3 with a standard 24-hour turnaround SLA.
- Batch Input: $0.30 / 1M tokens
- Batch Output: $1.25 / 1M tokens
- Ideal for: Offline classification, synthetic data generation, benchmark evals
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| AWS Region | Prompt Input $/1M | Completion Output $/1M | Cache Read $/1M | Batch Input $/1M | Pricing Tier |
|---|---|---|---|---|---|
| us-east-1 US East (N. Virginia) | $0.60 | $2.50 | — | $0.30 | Baseline |
| us-west-2 US West (Oregon) | $0.60 | $2.50 | — | $0.30 | Baseline |
| eu-central-1 EU (Frankfurt) | $0.72 | $3.00 | — | $0.36 | +20% vs Baseline |
| eu-west-1 EU (Ireland) | $0.72 | $3.00 | — | $0.36 | +20% vs Baseline |
| ap-northeast-1 Asia Pacific (Tokyo) | $0.73 | $3.03 | — | $0.36 | +22% vs Baseline |
| ap-southeast-3 Asia Pacific (Jakarta) | $0.72 | $3.00 | — | $0.36 | +20% vs Baseline |
| ap-south-1 Asia Pacific (Mumbai) | $0.71 | $2.94 | — | $0.36 | +18% vs Baseline |
| ap-southeast-2 Asia Pacific (Sydney) | $0.62 | $2.58 | — | $0.31 | +3% vs Baseline |
| eu-west-2 EU (London) | $0.93 | $3.88 | — | $0.47 | +55% vs Baseline |
| eu-south-1 EU (Milan) | $0.72 | $3.00 | — | $0.36 | +20% vs Baseline |
| eu-north-1 EU (Stockholm) | $0.72 | $3.00 | — | $0.36 | +20% vs Baseline |
| sa-east-1 South America (Sao Paulo) | $0.73 | $3.03 | — | $0.36 | +22% vs Baseline |
| us-east-2 US East (Ohio) | $0.60 | $2.50 | — | $0.30 | Baseline |
Developer Quickstart
Invoke Kimi K2 Thinking via Amazon Bedrock Converse APIimport boto3
# Amazon Bedrock Converse API invocation
client = boto3.client("bedrock-runtime", region_name="us-east-1")
response = client.converse(
modelId="moonshot-ai.kimi-k2-thinking-v1:0",
messages=[
{
"role": "user",
"content": [{"text": "Summarize key features and cost levers of Kimi K2 Thinking."}]
}
],
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")