Kimi K2 Thinking

Moonshot AI · Active · available in 7 of 16 regions

Batch inferenceStreaming Tool useVisionPrompt cachingEmbeddingsFine-tuning
Context window
Max output
Input / 1M
$0.600
us-east-1
Output / 1M
$2.50

Model & inference profile IDs

Base model ID — direct on-demand invoke

Pricing by region

USD per 1M tokens
Region Input Output Cache read Cache write Batch in Batch out Source
us-east-1 US East (N. Virginia) $0.600 $2.50 $0.300 $1.25 API
us-east-2 US East (Ohio) $0.600 $2.50 $0.300 $1.25 API
us-west-2 US West (Oregon) $0.600 $2.50 $0.300 $1.25 API
ap-southeast-2 Asia Pacific (Sydney) $0.618 $2.58 $0.309 $1.29 API
ap-northeast-1 Asia Pacific (Tokyo) $0.730 $3.03 $0.360 $1.52 API
ap-south-1 Asia Pacific (Mumbai) $0.710 $2.94 $0.360 $1.47 API
sa-east-1 South America (Sao Paulo) $0.730 $3.03 $0.360 $1.52 API

Region availability

TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.

Common questions

How much does Kimi K2 Thinking cost on Amazon Bedrock?
$0.600 per 1M input tokens and $2.50 per 1M output tokens in us-east-1.
Which AWS regions support Kimi K2 Thinking?
7 of 16 regions: us-east-1, us-east-2, us-west-2, ap-southeast-2, ap-northeast-1, ap-south-1, sa-east-1.
What is the model ID for Kimi K2 Thinking on Bedrock?
moonshot.kimi-k2-thinking.

Other Moonshot AI models