API docsModel reference

Grok Imagine Image 2.0 API

xAI Grok Imagine Image 2.0: bold, detailed images with low/medium quality tiers at 1K or 2K.

POST/api/v1/generationsBearer API key

grok-imagine-image-2.0Image · xAIModel details & pricing

Endpoints for this model

POST/generationsCreate a generation POST/images/generationsOpenAI-compatible images GET/generations/{id}Get the result POST/generations/{id}/cancelCancel a task POST/quoteQuote GET/models/{slug}Get one model

Parameter scope

Select a provider to see its effective parameter limits. Automatic routing chooses a provider that supports your input. Examples include defaults and required inputs; replace example media URLs with accessible files.

Request

cURL

curl 'https://01router.com/api/v1/generations' \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok-imagine-image-2.0",
  "input": {
    "prompt": "A cinematic landscape at sunrise.",
    "aspect_ratio": "1:1",
    "resolution": "1K",
    "quality": "medium",
    "num_images": 1
  }
}'

Input parameters

JSON body

For /generations and /quote, put these parameters inside input. For /images/generations, put them at the top level. Chat parameters go at the top level of /chat/completions.

model stringRequired: Model slug from the catalog. Project keys may use a project-specific model slug.
Allowed values:"grok-imagine-image-2.0"
input objectRequired: Model-specific input object. See the selected model reference for required fields, defaults and limits.
provider stringOptional: Optional provider slug. Omit for automatic routing; project settings may pin the provider.
project stringOptional: Optional project ID. Use its published model catalog and routing configuration.
callback_url string<uri>Optional: Public HTTPS URL, up to 1,000 characters. Receives the final generation object. Private network addresses are rejected.
input.prompt stringRequired
input.image_urls string<uri>[]Optional: Optional — switches to image editing
Maximum items:4
input.aspect_ratio enumOptional: Default:"1:1"
Allowed values:"1:1""16:9""9:16""4:3""3:4""3:2""2:3"
input.resolution enumOptional: Default:"1K"
Allowed values:"1K""2K"
input.quality enumOptional: Default:"medium"
Allowed values:"low""medium"
input.num_images integerOptional: Default:1
Minimum:1
Maximum:4

Response example

200 · application/json

{
  "id": "gen_example",
  "object": "generation",
  "model": "grok-imagine-image-2.0",
  "type": "image",
  "provider": "fal",
  "status": "processing",
  "input": {
    "prompt": "A cinematic landscape at sunrise.",
    "aspect_ratio": "1:1",
    "resolution": "1K",
    "quality": "medium",
    "num_images": 1
  },
  "outputs": [],
  "error": null,
  "credits": 100,
  "price_usd": 1,
  "created_at": "2026-10-25T08:00:00.000Z",
  "completed_at": null
}

Responses are illustrative. IDs, usage, prices and results depend on the actual request.

Response fields

id string: Generation ID returned by the create request.
object "generation": generation
model string: Model slug from the catalog. Project keys may use a project-specific model slug.
type video | image | audio | chat
provider string: Optional provider slug. Omit for automatic routing; project settings may pin the provider.
status string: queued / processing / succeeded / failed. Stop polling on succeeded or failed.
input object: Model-specific input object. See the selected model reference for required fields, defaults and limits.
outputs string[]: Result file URLs. Empty until available; download promptly because URLs may expire.
error string | null: Error message on failure; null otherwise.
credits number: Credits charged for this generation; zero after a refund.
price_usd number: Price of this generation in USD; zero after a refund.
created_at string: Creation time in ISO 8601 format.
completed_at string | null: Completion time in ISO 8601 format, or null while running.

Usage notes

Poll at intervals of at least 3 seconds. A 504 from the synchronous image endpoint means the task may still be running: poll its error.id instead of submitting it again.

Use with AI

Give your coding assistant the documentation index or the full API reference, including live model parameters.

llms.txt llms-full.txt This page as Markdown