Hub/Models/moonshotai/kimi-k2-thinking
moonshotaitext → text

MoonshotAI: Kimi K2 Thinking

Canonical ID: moonshotai/kimi-k2-thinking

Compare ModelOpen on OpenRouter →

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 in...

Artificial Analysis Benchmarks

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.60
Input
Completion Output (1M Tokens)
$2.50
Output
Prompt KV-Cache Read (1M Tokens)
$0.15
Cached
Context Window Capacity
256k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p