Video · xAI

Grok Imagine API

Grok Imagine API access for image and video generation from text, including text-to-image, image-to-image, text-to-video, and image-to-video.

可正常運作 · 6 variants · 由 $0.020
runapi.ai
curl -X POST https://runapi.ai/api/v1/grok_imagine/edit_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok-imagine-video-1.5-fast",
  "image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
  "prompt": "Generate a short video of a robot hand placing a chess piece on a board, dramatic lighting, slow motion."
}'
import { GrokImagineClient } from "@runapi.ai/grok-imagine";

const client = new GrokImagineClient();
const result = await client.editImage.run({
    model: "grok-imagine-video-1.5-fast",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a short video of a robot hand placing a chess piece on a board, dramatic lighting, slow motion.",
});
<?php

require __DIR__ . "/vendor/autoload.php";

use RunApi\GrokImagine\GrokImagineClient;

$client = new GrokImagineClient();
$result = $client->editImage->run([
        'model' => 'grok-imagine-video-1.5-fast',
        'image_url' => 'https://cdn.runapi.ai/public/samples/image.jpg',
        'prompt' => 'Generate a short video of a robot hand placing a chess piece on a board, dramatic lighting, slow motion.',
]);
require "runapi/grok_imagine"

client = RunApi::GrokImagine::Client.new
result = client.edit_image.run(
    model: "grok-imagine-video-1.5-fast",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a short video of a robot hand placing a chess piece on a board, dramatic lighting, slow motion."
)
npx skills add runapi-ai/grok-imagine -g
# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp

# Codex
codex plugin install runapi-mcp@agents

# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursor
@runapi.ai/grok-imagine v1
OVERVIEW

Grok Imagine is xAI's image and video generation suite covering text-to-image, edit-image, text-to-video, and image-to-video. It integrates with xAI's Grok intelligence to interpret complex, nuanced prompts.

  • 多個變體,對應不同速度/品質層級
  • Model skill 包含文件、schema 與 setup 備註
  • 支援 app-focused coding workflows
  • 生成失敗不收費
VARIANTS

比較所有 API 變體

Variant Billing From
grok-imagine-edit-image call $0.040 查看 →
grok-imagine-image-to-video second $0.020 查看 →
grok-imagine-text-to-image call $0.040 查看 →
grok-imagine-text-to-video second $0.020 查看 →
grok-imagine-video-1.5-fast call $0.750 查看 →
grok-imagine-video-1.5-preview second $0.020 查看 →
PRICING

Utility endpoints

Shared endpoints for this model line, such as extension, enhancement, or conversion actions.

Extend video
$0.10-$0.30 / video
Extension length: 6s · Output resolution: 480p $0.10
Extension length: 6s · Output resolution: 720p $0.20
Extension length: 10s · Output resolution: 480p $0.20
Extension length: 10s · Output resolution: 720p $0.30
Upscale image
$0.10 / request
SKILLS

為 app 開發安裝 Grok Imagine skill

將模型文件、schema、價格備註與 setup 步驟載入 coding workspace。

# Install the model skill for app development workflows
npx skills add runapi-ai/grok-imagine -g
Installs docs, schemas, pricing context, and setup notes into your developer workspace.
Or use this setup request in your coding tool:
Install the Grok Imagine skill for this app:

1. Add runapi-ai/grok-imagine with the skills installer.
2. Load SKILL.md in this workspace.
3. Use its docs, schemas, pricing notes, and setup steps when adding model features.
4. Confirm the install path when done.
運作方式

從 model skill 到第一次結果,只需四步

01

選擇模型

挑選符合輸出類型、品質門檻與延遲目標的模型與變體。

02

設定

設定 RunAPI key,並在 coding workspace 安裝 model skill。

03

開發

使用 skill 指引,在你的 app 內加入模型功能。

04

接收

透過 task ID 查詢、在支援時串流,或處理 webhook callback。

CONTEXT

Grok Imagine API 是甚麼?

Grok Imagine is xAI's creative AI suite built on Grok, covering image and video generation. Through RunAPI, all Grok Imagine endpoints share a single API key.

Provider
xAI
Modality
Video
點解揀 RunAPI

為何透過 RunAPI 使用 Grok Imagine API

一個驗證,對應所有 provider

一組 RunAPI key 即可解鎖整個 catalog。無需分開帳戶,亦無需為每個整合輪換密鑰。

統一定價與計費

按次以 USD 收費,每月結算。失敗的生成不會收費。

內含 schema 的 skill

型別化 schema 與 setup 備註打包在 model skill 內,讓實作從正確契約開始。

FAQ

常見問題

What creative modes does Grok Imagine support?

Text-to-image, edit-image, text-to-video, and image-to-video — covering still images, prompt-guided image edits, and motion generation.

Does Grok Imagine generate audio with video?

Yes — text-to-video generates synchronized native audio including dialogue with lip-sync.

How many reference images can I provide?

The edit-image endpoint accepts one source image for prompt-guided style transfer and composition editing.

What image styles are available?

Realistic, artistic, and anime styles across 5 aspect ratios. Style is controlled via the prompt and style parameter.

How long are generated videos?

6 to 15 seconds per generation (up to 30 seconds on the fast variant) for both text-to-video and image-to-video endpoints.

我應該先用邊個版本?

先選最平而且符合你質素要求的版本。大多數團隊會先用快速版本,之後再升級到 pro 用於正式生產。

有免費方案嗎?

新帳戶可獲得每個模型的首次呼叫免費。之後按次收費。

你哋支援串流結果嗎?

如有提供串流,RunAPI 會端到端串流。

失敗會點樣收費?

生成失敗不會收費。

輸出有快取嗎?

已生成輸出會儲存,並可按任務 ID 取回。輸入內容不會快取。

可以商業使用嗎?

可以——除非模型授權明確限制,否則每個版本都包括商業使用。相關限制會在版本頁面列明。

限流點樣計?

每個密鑰的限流會跟使用等級而提升。最新限制請參考定價頁。

可以在邊度報告問題?

可以在公開 GitHub repo 開 issue,或者電郵支援。

立即開始

開始用 Grok Imagine API 開發。