Image · Alibaba

Z Image

Ultra-fast text-to-image — photorealistic results in ~1 second with 8 inference steps.

Operational · 1 endpoints · a partir de $0.010

# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/z-image -g

The -g flag installs globally so every project picks it up.

Or paste this prompt to your AI agent:

Install the Z Image skill for me:

1. Clone https://github.com/runapi-ai/z-image
2. Copy the skills/z-image/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.

VISÃO GERAL

Z Image is Alibaba's ultra-fast text-to-image model that generates images in approximately one second using just 8 inference steps. It prioritizes generation speed while maintaining coherent, high-quality outputs.

Installable agent skill
Unified API key
SDK examples included
Gerações com falha não são cobradas

PREÇOS

Gerações com falha não são cobradas

Text to image

$0.01 / image

FICHA TÉCNICA

Model ID	z-image
Provedor	Alibaba
Modalidade	image
Task type	asynchronous
Cobrança	call
Endpoint	/api/v1/z_image/text_to_image
Commercial	Yes
Status	Operational

AGENT USAGE

Use this model from your agent

Prompt + SDK example

# User prompt to the agent
"Generate a clean product shot of white sneakers on a gradient background, studio lighting."

// Code generated by the agent via @runapi.ai/z-image
import { ZImageClient } from '@runapi.ai/z-image';

const client = new ZImageClient();
const result = await client.textToImage.run({
  model: 'z-image',
  prompt: 'Generate a clean product shot of white sneakers on a gradient background, studio lighting.',
});

@runapi.ai/z-image npm

COMO FUNCIONA

How to call this model

Install the skill

Add the model skill to your agent or install the SDK package.

Authenticate once

Use your RunAPI key for every supported model.

Send a request

Use the unified schema for the endpoint you need.

Receive output

Poll by task ID or handle the callback when the generation completes.

SDK QUICKSTART

SDK quickstart

runapi.ai

curl -X POST https://runapi.ai/api/v1/z_image/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "z-image",
  "prompt": "Generate a clean product shot of white sneakers on a gradient background, studio lighting."
}'

import { ZImageClient } from "@runapi.ai/z-image";

const client = new ZImageClient();
const result = await client.textToImage.run({
    model: "z-image",
    prompt: "Generate a clean product shot of white sneakers on a gradient background, studio lighting.",
});

require "runapi/z_image"

client = RunApi::ZImage::Client.new
result = client.text_to_image.run(
    model: "z-image",
    prompt: "Generate a clean product shot of white sneakers on a gradient background, studio lighting."
)

@runapi.ai/z-image v1

CONTEXTO

Where Z Image fits

Z Image is Alibaba's speed-optimized text-to-image model, generating results in ~1 second. Through RunAPI, it shares the same API shape and billing as all Alibaba models.

Provider

Alibaba

Modality

Image

POR QUE RUNAPI