Grok Imagine Text to Image API

POST /v1/tasks

All models are called through the Unified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	grok-imagine/text-to-image
Type	Image generation (text-to-image)
Routes	default / quality
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

Grok Imagine text-to-image: fast and low-cost with 13 aspect ratios and flat 1k/2k pricing; the standalone quality-tier model (grok-imagine-quality/text-to-image) delivers hero-grade output with resolution-tiered pricing.

Production guidance

For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Fast, low-cost generation

The standard model optimizes speed and cost — ideal for batches and ideation.

prompt

13 aspect ratios

From 2:1/20:9 ultra-wide to 9:20 extra-tall, covering every social format.

aspect_ratio

1k/2k same price

On the standard model, resolution does not change the price — just use 2k.

resolution

Quality-tier sibling model

For hero-grade detail, switch to grok-imagine-quality/text-to-image (xAI official quality model), billed in 1k/2k tiers.

prompt

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok-imagine/text-to-image",
  "input": {
    "prompt": "A red panda tea master in a tiny mountain teahouse pouring glowing amber tea, steam curling into soft light",
    "aspect_ratio": "16:9",
    "resolution": "2k",
    "output_format": "jpeg"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "grok-imagine/text-to-image",
  "input": {
    "prompt": "A red panda tea master in a tiny mountain teahouse pouring glowing amber tea, steam curling into soft light",
    "aspect_ratio": "16:9",
    "resolution": "2k",
    "output_format": "jpeg"
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "grok-imagine/text-to-image",
  "input": {
    "prompt": "A red panda tea master in a tiny mountain teahouse pouring glowing amber tea, steam curling into soft light",
    "aspect_ratio": "16:9",
    "resolution": "2k",
    "output_format": "jpeg"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value grok-imagine/text-to-image.

example grok-imagine/text-to-image

input object required

Business parameters. Put Grok Imagine Text to Image-specific configuration here.

prompt string required

Text description of the image to generate.

aspect_ratio enum optional

Aspect ratio of the generated image.

default 1:1 enum: 2:120:919.5:916:94:33:21:12:33:49:16 +3

resolution enum optional

Output image resolution.

default 1k enum: 1k2k

output_format enum optional

Output image format.

default jpeg enum: jpegpngwebp

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Red panda tea master (2k)

Tested on the standard model with full parameters at 16:9.

Request body

{
  "model": "grok-imagine/text-to-image",
  "input": {
    "prompt": "A red panda tea master in a tiny mountain teahouse pouring glowing amber tea, steam curling into soft light",
    "aspect_ratio": "16:9",
    "resolution": "2k",
    "output_format": "jpeg"
  }
}

Getting the result

The response returns a taskId immediately without waiting for generation to finish.
In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
When status=success, download the generated image from output[].url.
When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

Standard vs quality tier?

Standard (grok-imagine/text-to-image) is fast and cheap for volume; the quality-tier model (grok-imagine-quality/text-to-image) has richer detail with 1k/2k tiered pricing.

How do I get higher quality?

Use the standalone quality-tier model grok-imagine-quality/text-to-image (xAI official quality model) — same parameters, priced by 1K/2K resolution tiers.

Does it take reference images?

Use grok-imagine/image-to-image for reference-based edits.