Grok Imagine Video
Frontier labVideo
API id
grok-imagine-videoInput / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
2 listings
Released
-
date not published
Where to run it
2 hosts serve Grok Imagine Video. The comparison is on blended price, 3 parts input to 1 part output.
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- ImagesTextVideo
- Produces
- Video
Similar models
This model has no listed price, so these are current models with similar capabilities.
Smaller xAI models
No similar xAI model keeps its key capabilities.
Other frontier labs
No similar match from another frontier lab.
Open-weight picks
No similar open-weight match.
Call it
Using xAI's API.
Python
import os
from openai import OpenAI
client = OpenAI(base_url="https://api.x.ai/v1", api_key=os.environ["XAI_API_KEY"])
completion = client.chat.completions.create(
model="grok-imagine-video",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)Python
from litellm import completion
response = completion(
model="xai/grok-imagine-video",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
Which APIs offer Grok Imagine Video?
Grok Imagine Video runs on 2 APIs: xAI and Replicate.
Is Grok Imagine Video being retired?
No retirement date is scheduled for it on any API we track.
What is Grok Imagine Video's API model id?
Use grok-imagine-video with xAI.
Sources
Raw catalog entry for grok-imagine-video on xAI
{
"input_cost_per_image": 0.002,
"litellm_provider": "xai",
"mode": "video_generation",
"output_cost_per_second": 0.05,
"output_cost_per_second_480p": 0.05,
"output_cost_per_second_720p": 0.07,
"source": "https://docs.x.ai/docs/models/grok-imagine-video",
"supported_modalities": [
"text",
"image",
"video"
],
"supported_output_modalities": [
"video"
]
}