EN / 中文
Model prices / Moonshot AI / Kimi K2 Thinking

Kimi K2 ThinkingOpen weights

Moonshot AI · released 2025-11-06

No price from the maker itself is on record for Kimi K2 Thinking. The lowest of 15 providers is Helicone: $0.48 per 1M input tokens and $2 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 262K output tokens per request.

Price by providerUSD per 1M tokens

ProviderInputOutputCachedNotes
HHeliconeLowestkimi-k2-thinking
$0.48$2—LowestOfficial docs
3302.AIkimi-k2-thinking
$0.575$2.3—Official docs
EEden AIamazon/moonshot.kimi-k2-thinking
$0.6$2.5—Official docs
Hugging Facemoonshotai/Kimi-K2-Thinking
$0.6$2.5$0.15Official docs
IO.NETmoonshotai/Kimi-K2-Thinking
$0.6$2.5$0.3Official docs
KKilo Gatewaymoonshotai/kimi-k2-thinking
$0.6$2.5$0.15Official docs
NNanoGPTmoonshotai/kimi-k2-thinking
$0.6$2.5$0.15Official docs
Novita AImoonshotai/kimi-k2-thinking
$0.6$2.5$0.15Official docs
OpenRoutermoonshotai/kimi-k2-thinking
$0.6$2.5$0.15Official docs
MMeganovamoonshotai/Kimi-K2-Thinking
$0.6$2.6—Official docs
AI/ML APImoonshotai/kimi-k2-thinking
$0.6348$2.645$0.1587Official docs
QQiniuDeprecatedmoonshotai/kimi-k2-thinking
$0.57971$2.318841—DeprecatedOfficial docs
3 more listings
ProviderInputOutputCachedNotes
OpenCodeDeprecatedkimi-k2-thinking
$0.4$2.5$0.4DeprecatedOfficial docs
Amazon BedrockDeprecatedmoonshot.kimi-k2-thinking
$0.6$2.5—DeprecatedOfficial docs
PoeDeprecatednovita/kimi-k2-thinking
———DeprecatedOfficial docs

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

About

Thinking Kimi model for slower research passes, planning, and hard technical questions

Description from models.dev.

Specs

Type
Text
Context
262K
Max output
262K
Input
Text
Output
Text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Knowledge cutoff
2024-08
Open weights
Yes
Released
2025-11-06

Source

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.