Kimi K2 Thinking

moonshot.kimi-k2-thinking

Reasoning

Model details

Model: moonshot.kimi-k2-thinking
Provider: amazon-bedrock
API: bedrock-converse-stream
Base URL: https://bedrock-runtime.us-east-1.amazonaws.com
Input: text
Reasoning: Yes
Context window: 262,143
Max tokens: 16,000

Pricing

USD per million tokens.

Input: $0.6
Output: $2.5
Cache read: $0
Cache write: $0

A reference estimate. Provider pricing and context tiers may vary.

PLAN YOUR USAGE

Session cost calculator

Estimate the model requests made during an agent session.

Session shape

Model requests

Starting context

Context added / request

Output / request

Warm-request cache reuse96%

Starting context is already cached

Bill uncached reusable context as cache writes

Estimated session$0.09

Uncached input: $0.05
Cache reads: $0.0000
Cache writes: $0.0000
Output: $0.04
Without caching: $0.47

25 model requests

The first request starts cold unless marked otherwise. Output is billed separately from context growth. Providers differ in eligibility, context tiers, rounding, and retention.

Compatibility flags

supportsStrictMode: Yes

Kimi K2 Thinking

Model details

Show configuration

Pricing

Session cost calculator

Compatibility flags