---
id: "moonshotai/kimi-k3.1-pro"
also: ["moonshotai/kimi-k3.1-pro-20261023", "moonshotai/Kimi-K3.1-Pro", "requesty/moonshot/kimi-k3.1-pro", "vercel/moonshotai/kimi-k3.1-pro"]
card_usd_per_m: "2.0 in, 10.0 out, at moonshotai/mxfp4"
cheapest_list_usd_per_m: "0.303 in, 10.0 out, at wafer/us on openrouter"
cheapest_effective_usd_per_m: "0.2075 in, 8.1953 out, at relace on vercel"
context: 1048576
max_output: 943718
input: ["text", "image", "video"]
output: ["text"]
released: "2026-10-23"
reasoning: ["max", "high", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 48
gateways: "openrouter (24), vercel (17), requesty (7)"
no_training: 46
trains: 2
retains_prompts: 5
intelligence: 46.5000
---
# MoonshotAI: Kimi K3.1 Pro

Kimi K3.1 Pro is the first model in the K3.1 series and Kimi's most capable flagship to date, a 3T class model with native visual understanding and a 1M token context window. It brings substantial gains in coding, 3D creation, financial research and modeling, and suits software engineering, knowledge work and deep reasoning.