Skip to content
AWS Bedrock

Moonshot.Kimi K2 Thinking

Moonshot.Kimi K2 Thinking is available via AWS Bedrock with a 128K context window and up to 8,192 output tokens. Pricing: $0.6000/1M input tokens, $2.50/1M output tokens.

Moonshot.Kimi K2 Thinking Pricing & Specifications

Input Price$0.60 per 1M tokens
Output Price$2.50 per 1M tokens
Context Window128,000 tokens (128K)
Max Output8,192 tokens
ProviderAWS Bedrock

What is Moonshot.Kimi K2 Thinking?

Moonshot.Kimi K2 Thinking is a large language model by AWS Bedrock with a 128K context window and up to 8,192 output tokens. It costs $0.60 per 1M input tokens and $2.50 per 1M output tokens. Moonshot.Kimi K2 Thinking is available via AWS Bedrock with a 128K context window and up to 8,192 output tokens. Pricing: $0.6000/1M input tokens, $2.50/1M output tokens.

Capabilities

text reasoning

Moonshot.Kimi K2 Thinking Cost Examples

Short prompt (500 tokens)

$0.000300

Medium prompt (2K tokens)

$0.00120

Long output (4K tokens)

$0.01000

Count tokens for Moonshot.Kimi K2 Thinking

Paste your prompt to see exact token counts and API cost estimates.

Open Token Counter

Similar Models to Moonshot.Kimi K2 Thinking

AWS Bedrock

Us.Writer.Palmyra X5

$0.60/1M in 1M ctx

AWS Bedrock

Writer.Palmyra X5

$0.60/1M in 1M ctx

AWS Bedrock

Ap Northeast 1/Qwen.Qwen3 Coder Next

$0.60/1M in 262K ctx

AWS Bedrock

Moonshotai.Kimi K2.5

$0.60/1M in 262K ctx

Frequently Asked Questions

How much does Moonshot.Kimi K2 Thinking cost per token? +
Moonshot.Kimi K2 Thinking costs $0.60 per 1M input tokens and $2.50 per 1M output tokens. For a typical 1,000-token request with a 500-token response, that works out to roughly $0.001850.
What is the context window for Moonshot.Kimi K2 Thinking? +
Moonshot.Kimi K2 Thinking supports a context window of 128,000 tokens (128K). This determines the maximum combined length of your prompt and conversation history in a single API call.
What is the maximum output length for Moonshot.Kimi K2 Thinking? +
Moonshot.Kimi K2 Thinking can generate up to 8,192 tokens in a single response. If you need longer outputs, you can make multiple API calls and concatenate the results.
Is Moonshot.Kimi K2 Thinking good for coding tasks? +
Moonshot.Kimi K2 Thinking can handle basic coding tasks, but there are models specifically optimized for code generation that may perform better on complex programming problems.
Token Counter | Pricing Calculator | Model Comparison | All AWS Bedrock Models