Kimi K2 Thinking pricing & specs

Moonshot AI · released 2025-11-06 · ● verified 2026-10-11

input / 1M$0.60via Amazon Bedrock
output / 1M$2.50via Amazon Bedrock
context262.1K
max output16K

// price history ($/1M tokens)

$2.875
input $/1Moutput $/1M2025-11-06 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs Kimi K2 Thinking
Gemma 4 E2B IT$0.04$0.08131.1K−95.3%
Qwen3.7 Flash$0.03$0.131M−94.9%
Qwen Turbo$0.05$0.201M−91.9%
DeepSeek V4 Flash 0731$0.06$0.181.05M−91.6%
GPT OSS 120B$0.05$0.25131.1K−90.7%
DeepSeek V4 Pro vs Kimi K2 Thinking →

// price by host

hostin $/1Mout $/1M
Amazon Bedrock$0.60$2.50
Novita AI$0.60$2.50

// faq

How much does Kimi K2 Thinking cost?

Kimi K2 Thinking costs $0.60 per million input tokens and $2.50 per million output tokens (cheapest tracked host: Amazon Bedrock). At 50M input and 10M output tokens per month that is about $55.00.

What is the context window of Kimi K2 Thinking?

262.1K tokens, with up to 16K output tokens per request.

What are cheaper alternatives to Kimi K2 Thinking?

Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out) offer the same input types and capabilities for less.

Is Kimi K2 Thinking open weights?

Yes. It is available from 2 tracked hosts; the cheapest is Amazon Bedrock at $0.60 input and $2.50 output per million tokens.

// spec sheet

input / 1M
$0.60
output / 1M
$2.50
blended (3:1)
$1.075
context
262.1K
max output
16K
input types
text
reasoning
yes
tool calling
yes
structured output
yes
open weights
yes
knowledge cutoff
2024-08
price source
Amazon Bedrock

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Gemma 4 E2B IT$0.04$0.08$2.80
Qwen3.7 Flash$0.03$0.13$2.80
Qwen Turbo$0.05$0.20$4.50
Kimi K2 Thinking$0.60$2.50$55.00

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.