xAI: Grok Imagine Image 2.0

x-ai/grok-imagine-image-2.0

Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and medium quality modes.

vision

MODALITIES

→

INPUT PRICE

—

OUTPUT PRICE

—

CONTEXT

65.5K

RELEASED

Aug 12, 2026

Provider					Chat
AnyRouter	$0.01/call	—	Hit rate— Cache read$0.2	100.0%

Capabilities

Input modalities

imagetext

Output modalities

image

Features

logprobsmax_tokensresponse_formatseedtemperaturetop_logprobstop_p

Get API Key

Create an API key from the Keys page, then set it as an environment variable:

export ONLIST_API_KEY=sk-...

Make your first request

Endpoints

POSThttps://onlist.io/v1/images/generations

Request Headers

Authorization:Bearer $ONLIST_API_KEY

Content-Type:application/json

Model:x-ai/grok-imagine-image-2.0

Code samples

curl https://onlist.io/v1/images/generations \
  -H "Authorization: Bearer $ONLIST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "model": "x-ai/grok-imagine-image-2.0",
       "prompt": "A white siamese cat",
       "n": 1,
       "size": "1024x1024"
     }'

Replace $ONLIST_API_KEY with the API key from your Keys page.

Authentication

All requests must include an Authorization: Bearer <TOKEN> header. Generate keys from the Keys page; keys can be scoped to specific models, groups, IP ranges, and rate limits.

Supported parameters

Name	Type	Description
`logprobs`	boolean	Whether to return log probabilities of the output tokens.
`max_tokens`	integer	Maximum number of tokens to generate in the completion.
`response_format`	object	Specifies the output format. Use {"type": "json_object"} for JSON mode.
`seed`	integer	If specified, the system will attempt deterministic sampling for reproducible results.
`temperature`	number	Sampling temperature between 0 and 2. Higher values make output more random.
`top_logprobs`	integer	Number of most likely tokens to return at each position (0-20). Requires logprobs: true.
`top_p`	number	Nucleus sampling. The model considers tokens with top_p probability mass.

These are the request parameters this model accepts. Parameter semantics follow the OpenAI Chat Completions specification.