---
id: "moonshotai/kimi-k2-thinking"
also: ["moonshotai/kimi-k2-thinking-20251106", "moonshotai/Kimi-K2-Thinking", "vercel/moonshotai/kimi-k2-thinking"]
cheapest_list_usd_per_m: "0.47 in, 2.0 out, at deepinfra on vercel"
cheapest_effective_usd_per_m: "0.3591 in, 2.0 out, at deepinfra on vercel"
context: 262144
max_output: 98304
input: ["text"]
output: ["text"]
released: "2025-11-06"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 3
gateways: "openrouter (2), vercel (1)"
no_training: 3
trains: 0
retains_prompts: 0
coding: 21
---
# MoonshotAI: Kimi K2 Thinking

Kimi K2 Thinking is an advanced open-source thinking model by Moonshot AI. It can execute up to 200 – 300 sequential tool calls without human interference, reasoning coherently across hundreds of steps to solve complex problems. Built as a thinking agent, it reasons step by step while using tools, achieving state-of-the-art performance on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks, with major gains in reasoning, agentic search, coding, writing, and general capabilities.