Model catalog profile

MoonshotAI: Kimi K2 Thinking | model profile

Use this MoonshotAI: Kimi K2 Thinking profile to review provider, region, modality, pricing, and the next route before deciding whether to keep exploring the model.

Provider

Moonshot AI

4 models in catalog

Context

262,144

China model route

Input

$0.60

USD / 1M tokens

Output

$2.5

USD / 1M tokens

What this page answers

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced

Moonshot AI · moonshotai/kimi-k2-thinking
text->text · China model route
262,144 context · $0.60 input

Before connecting

Do not stop at the model name. Before integration, verify base URL, protocol, visible models, parameters, and limits together.

supports frequency_penalty
supports include_reasoning
supports logit_bias
supports max_tokens
supports min_p

Next action

After this page, the usual next step is to open the model profile, the provider profile, or run a key check to confirm the real callable range.

Check whether the model fits the use case
Then verify key permission and callable models

Continue

moonshotai/kimi-k2-thinking