Grok Imagine grok-imagine-text-to-video API
A model variant exposed through RunAPI's unified AI API.
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/grok-imagine -g
Install the Grok Imagine skill for me: 1. Clone https://github.com/runapi-ai/grok-imagine 2. Copy the skills/grok-imagine/ 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.
Grok Imagine grok-imagine-text-to-video is available through the same RunAPI auth, SDKs, and agent skill workflow.
- Unified endpoint
- SDK snippets
- Agent install path
- Gerações com falha não são cobradas
PREÇOS
FICHA TÉCNICA
| Model ID | grok-imagine-text-to-video |
| Provedor | xAI |
| Modalidade | video |
| Task type | asynchronous |
| Cobrança | second |
| Endpoint | /api/v1/grok_imagine/text_to_video |
| Commercial | Yes |
| Status | Operational |
Quickstart — grok-imagine-text-to-video
curl -X POST https://runapi.ai/api/v1/grok_imagine/text_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-text-to-video",
"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.textToVideo.run({
model: "grok-imagine-text-to-video",
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.text_to_video.run(
model: "grok-imagine-text-to-video",
prompt: "Generate a short video of a robot hand placing a chess piece on a board, dramatic lighting, slow motion."
)
How to use grok-imagine-text-to-video
Choose endpoint
Pick the endpoint and copy the SDK snippet.
Pass model ID
Use this variant ID in the request body.
Run task
Submit the request and store the returned task ID.
Collect output
Poll or receive the callback when the task finishes.
How grok-imagine-text-to-video compares
6–10s video from text with synchronized native audio and lip-sync
Prompt-guided style transfer and composition editing from one source image
6–10s video from text with synchronized native audio and lip-sync
Input image becomes frame 1; animates with motion + camera
6–10s video from text with synchronized native audio and lip-sync
Aurora model; 7 aspect ratios; realistic/artistic/anime styles
Where to use this variant
Product video
Generate short production-ready clips from prompts.
Creative iteration
Test multiple directions quickly.
Agent workflows
Let agents create video assets via tool calls.
Frequently asked questions about grok-imagine-text-to-video
How do I select grok-imagine-text-to-video?
Pass the model ID shown in the quickstart.
Is pricing usage-based?
Yes. Pricing is metered per call or unit.