MoonshotAI: Kimi K2.5
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.
Specifications
| Context Window | 262K |
| Modalities | text, vision |
| Status | available |
| Category | third-party |
| Model ID | moonshotai/kimi-k2.5 |
Quick Start
import OpenAI from 'openai'
const client = new OpenAI({
apiKey: process.env.HANZO_API_KEY,
baseURL: 'https://api.hanzo.ai/v1'
})
const response = await client.chat.completions.create({
model: 'moonshotai/kimi-k2.5',
messages: [{ role: 'user', content: 'Hello!' }]
})
console.log(response.choices[0].message.content)from openai import OpenAI
client = OpenAI(
api_key=os.environ["HANZO_API_KEY"],
base_url="https://api.hanzo.ai/v1"
)
response = client.chat.completions.create(
model="moonshotai/kimi-k2.5",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)curl https://api.hanzo.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $HANZO_API_KEY" \
-d '{
"model": "moonshotai/kimi-k2.5",
"messages": [{"role": "user", "content": "Hello!"}]
}'package main
import (
"context"
"fmt"
"os"
"github.com/sashabaranov/go-openai"
)
func main() {
cfg := openai.DefaultConfig(os.Getenv("HANZO_API_KEY"))
cfg.BaseURL = "https://api.hanzo.ai/v1"
client := openai.NewClientWithConfig(cfg)
resp, _ := client.CreateChatCompletion(context.Background(),
openai.ChatCompletionRequest{
Model: "moonshotai/kimi-k2.5",
Messages: []openai.ChatCompletionMessage{
{Role: openai.ChatMessageRoleUser, Content: "Hello!"},
},
},
)
fmt.Println(resp.Choices[0].Message.Content)
}More from Moonshot AI
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 Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift. It sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.
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 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.
Use MoonshotAI: Kimi K2.5 via Hanzo AI
One API key. 390+ models. OpenAI-compatible. Start free.