Moonshot AI: Kimi K2 Thinking

Coming soonQuick Start

Kimi K2 Thinking is Moonshot AI's open reasoning model, released 2025-11, extending the K2 series into long-horizon agentic workflows. Built on a trillion-parameter mixture-of-experts architecture, it activates 32 billion parameters per forward pass and interleaves step-by-step reasoning with tool use across hundreds of turns. It sets benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench.

This model is not routed on MirAPI yet — prices shown are the official list prices. Create an account to get notified when it goes live.

Modalities
inTextoutText
Price / 1M
$0.60 / $2.50
Context
262K
Knowledge cutoff

Capabilities

ReasoningTool useLong contextPrompt cachingStructured output

Benchmarks

bar = score (0–100) · ▏ median

Scores from vendor reports and public leaderboards. No private evals.

Coding Index
Code
21.0
#72
GPQA Diamond
Science QA
83.4
#37
τ-bench (airline)
Agentic tool use
69.2
#51

Showcase

Three fixed prompts, identical for every chat model. Outputs are archived verbatim — copy the prompt to reproduce.

Task prompt · identical for all models
Build a single-file HTML page using three.js from a CDN: a low-poly planet with a tilted ring of ~200 orbiting particles, a soft key light plus rim light, slow auto-rotation, and drag-to-orbit controls. No build tools — one file only.
Archived output
Archive not published yet

Every model will run this exact prompt; the output lands here verbatim, with tokens and per-run cost.

Quick Start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="moonshotai/kimi-k2-thinking",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire Kimi K2 Thinking into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free