---
id: "moonshotai/kimi-k2-0905"
also: ["moonshotai/kimi-k2-0905", "moonshotai/Kimi-K2-Instruct-0905", "hf/moonshotai/Kimi-K2-Instruct-0905"]
cheapest_list_usd_per_m: "0.6 in, 2.5 out, at novita on hf"
cheapest_effective_usd_per_m: "0.5999 in, 2.4986 out, at novita/fp8 on openrouter"
context: 262144
max_output: 98304
input: ["text"]
output: ["text"]
released: "2025-09-04"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 2
gateways: "hf (1), openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 0
---
# MoonshotAI: Kimi K2 0905

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...