Hanzo · ultra

Zen5 Pro

Zen Flash IQ2_XXS-imatrix weights (81 GB GGUF on zenlm/zen-5-pro-gguf).

Get API key Try in Chat

Specifications

Context Window1M

ArchitectureMoE

Modalitiestext

Price…

Model IDzen5-pro

1M context window · 284B total / 37B active (MoE) · Zen Flash base · IQ2_XXS-imatrix quant (81 GB) · Runs on 128 GB hardware

Quick start

Get an API key →

TypeScript

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: 'zen5-pro',
  messages: [{ role: 'user', content: 'Hello!' }]
})

console.log(response.choices[0].message.content)

Python

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="zen5-pro",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

cURL

curl https://api.hanzo.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -d '{
    "model": "zen5-pro",
    "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: "zen5-pro",
            Messages: []openai.ChatCompletionMessage{
                {Role: openai.ChatMessageRoleUser, Content: "Hello!"},
            },
        },
    )
    fmt.Println(resp.Choices[0].Message.Content)
}