Grok Imagine Image 2.0 API

xAI-Image GenerationLive

From $0.030 / image (1K Low)-25%$0.040 official price

Text-to-ImageImage EditingMulti-Reference Composition1-10 Images per Request13 Aspect Ratios1K / 2K Output

Route state

LiveAsync Task Tracking

Model Highlights

Generation and editing in one model, from $0.03 per image

Use Cases

Social creatives, ads, batch variations, reference-based edits

Input

Text prompt with optional 1-3 input images

Output

1-10 images per request

Playground Pricing About API

Try Grok Imagine Image 2.0 before you integrate the API.

Test output quality, estimate credit usage, and generate samples before you formally integrate.

Create image task

Fixed to grok-imagine-image-2.0

Grok Imagine Image 2.0From $0.030/image - 2.04 cr/image (1K Low)

Prompt

A cinematic, photorealistic late-night workspace in a near-future city.

A developer sits casually at a clean desk beside a large rain-covered window, focused on a laptop. Outside, the city glows softly through the rain with restrained cyan, emerald-green and occasional violet light. The atmosphere feels slightly cyberpunk, but realistic and lived-in rather than futuristic fantasy.

The room is quiet and minimal: dark graphite surfaces, a mechanical keyboard, a half-finished cup of coffee, subtle cable details, soft reflections on glass and brushed metal. Natural posture, realistic hands, authentic skin texture, understated clothing, candid documentary feeling.

The laptop screen shows a clean dark interface with the small word “EvoLink” in the corner, spelled exactly and clearly. No large logo, no slogan, no floating holograms, no obvious network diagrams.

Soft emerald #00FF88 and cyan #00D4FF screen light gently illuminate the developer’s face and hands, with a very subtle violet #7C3AED accent in the distant city. Moody cinematic lighting, realistic rain reflections, shallow depth of field, medium-format editorial photography, premium technology brand aesthetic, sophisticated and understated.

No excessive neon, no crowded cyberpunk signs, no sci-fi armor, no dramatic holograms, no fake interface text, no extra words, no malformed hands, no plastic skin, no oversaturated colors.

Input images

Optional. Add 1-3 images to switch to editing mode. Each input image is billed once per request.

0/3 files

Aspect ratio

Quality

Resolution

Images (n)1

110

Estimate $0.0453.06 cr

1K Medium x 1 image + 0 input images

Ready

History

Generated Grok Imagine Image 2.0 tasks will appear here.

Know your testing cost before you add credits.

Pricing is a simple matrix of resolution (1K/2K) and quality (Low/Medium). Start from the cost of a single sample and pick a testing budget.

First Test Cost

Text-to-Image - 1K - Low quality

1K Low prompt-only

Credits2.04

One 1K Low prompt-only image

Approx. Cost$0.030

About 333 tests with $10 in credits.

Start with the 1K Low tier for drafts, then switch to Medium or 2K for the final check. Input images add a per-image fee once per request.

EvoLink rate$0.030

official price$0.040

You save-25%

Testing Budget Guide

Pick an amount based on how many tests you expect.

Add Credits

$10

About 333 tests

Good for a first validation.

$50

About 1667 tests

Good for prompt iteration.

$100

About 3333 tests

Good before production integration.

Common Cost Examples

Draft iteration1K Low prompt-only

$0.030/image-25%

2.04 cr/image$0.040 official price

Reference edit1K Medium + one input image

$0.053/image-25%

3.57 cr/image$0.070 official price

Final quality check2K Medium prompt-only

$0.060/image-25%

4.08 cr/image$0.080 official price

Estimated cost for one generated image. Multiply the output rate by n for multi-image requests; input image fees are charged once per request.

Model Pricing

Item	Rule	Rate	Billing
1K · Low	Fastest tier (~10s) for drafts and prompt iteration.	$0.030/image-25% 2.04 cr/image$0.040 official price	Per output image
1K · Medium (default)	Default tier with better detail; generation may take 10-75s.	$0.045/image-25% 3.06 cr/image$0.060 official price	Per output image
2K · Low	Higher resolution with the fast quality tier.	$0.045/image-25% 3.06 cr/image$0.060 official price	Per output image
2K · Medium	Highest tier for final quality checks.	$0.060/image-25% 4.08 cr/image$0.080 official price	Per output image

1K · Low

Fastest tier (~10s) for drafts and prompt iteration. - Per output image

$0.030/image-25%

2.04 cr/image$0.040 official price

1K · Medium (default)

Default tier with better detail; generation may take 10-75s. - Per output image

$0.045/image-25%

3.06 cr/image$0.060 official price

2K · Low

Higher resolution with the fast quality tier. - Per output image

$0.045/image-25%

3.06 cr/image$0.060 official price

2K · Medium

Highest tier for final quality checks. - Per output image

$0.060/image-25%

4.08 cr/image$0.080 official price

Optional Add-ons & Billing NotesInput image pricing and multi-image requests.

Item	Rule	Rate	Billing
Input images	Applied to each input image in image_urls (max 3), charged once per request regardless of n.	$0.0075/image-25% 0.51 cr/image$0.010 official price	Per input image
Multiple outputs (n)	n can be 1-10. The output rate is multiplied by n; failed tasks are not charged.	Output rate × n	Per request

Grok Imagine Image 2.0 capabilities for production image workflows

Generate images from text or edit them with up to 3 reference images in one model. The mode switches automatically based on the number of input images, with matrix-priced Low/Medium quality and 1K/2K resolution, and up to 10 images per request.

More prompt examples

Input

Text / 1-3 images

Output

1-10 images

Aspect ratio

13 presets + auto

Quality x Resolution

Low/Medium x 1K/2K

Grok Imagine Image 2.0 guides and comparisons

Confirmed features and release notesSee what is documented for the EvoLink route and what still requires output testing.API integration guideGo from an API key to generation, editing, task polling, callbacks, and failure handling.Grok Imagine Image 2.0 vs GPT Image 2Compare documented controls, reference workflows, output sizes, and production routing.

Core image capabilities

Create a commercial visual from one prompt

Build an art-directed campaign scene from text, then adapt the concept across 13 aspect-ratio presets.

Capability illustration created with GPT Image 2; Grok outputs vary by prompt, reference images, and settings.

Direct an edit with a reference image

Preserve the main subject while changing the environment, lighting, materials, or visual direction.

Capability illustration created with GPT Image 2; Grok outputs vary by prompt, reference images, and settings.

Compose from multiple references

Combine 2-3 sources—such as a subject, product, and environment—into one coherent image with indexed references.

Capability illustration created with GPT Image 2; Grok outputs vary by prompt, reference images, and settings.

What You Can Do

Generate Marketing Visuals

Create ads, posters, and social creatives from a prompt in 13 aspect ratios.

Edit With Input Images

Pass 1-3 images in image_urls to switch to editing mode - no separate edit model name.

Batch Variations With n

Generate up to 10 images in one request; the output rate scales by n while input fees stay flat.

Control Cost by Tier

Iterate on Low quality at 1K, then switch to Medium or 2K for final output.

Grok Imagine Image 2.0 vs other image models

Feature	Grok Imagine Image 2.0	Seedream 5.0 Pro	GPT Image
Starting price	~$0.030 / image	From ~$0.034 / image	Token or tier based
Output tiers	Low/Medium x 1K/2K	1K / 2K	Quality tiers
Reference input	Up to 3 images	Up to 10 images	Supported
Images per request	1-10	1	Model dependent
Best for	Fast iteration, batch creatives, reference edits	Ads, product creative, image editing	OpenAI image workflows

Starting price

Grok Imagine Image 2.0~$0.030 / image

Seedream 5.0 ProFrom ~$0.034 / image

GPT ImageToken or tier based

Output tiers

Grok Imagine Image 2.0Low/Medium x 1K/2K

Seedream 5.0 Pro1K / 2K

GPT ImageQuality tiers

Reference input

Grok Imagine Image 2.0Up to 3 images

Seedream 5.0 ProUp to 10 images

GPT ImageSupported

Images per request

Grok Imagine Image 2.01-10

Seedream 5.0 Pro1

GPT ImageModel dependent

Best for

Grok Imagine Image 2.0Fast iteration, batch creatives, reference edits

Seedream 5.0 ProAds, product creative, image editing

GPT ImageOpenAI image workflows

Model ID, reference inputs, and output limits

Exact model ID, two image modes

Use model ID grok-imagine-image-2.0. Send a prompt alone for text-to-image, or add 1-3 input images to switch to editing without a separate edit model ID.

Quality and resolution are independent

quality (low/medium) controls generation effort and speed; resolution (1k/2k) controls output pixels. Both enter the price matrix - the four combinations are priced 1x / 1.5x / 1.5x / 2x of base.

Input fees are charged once

Each input image adds 0.25x base per request, regardless of how many outputs you request with n. Failed tasks are not charged.

Why use Grok Imagine Image 2.0 through EvoLink

Live cost before generation

Review the current price and estimated credits before submitting a task, based on resolution, quality, output count, and reference images.

Unified API

One API key works across Grok, Seedream, Nano Banana, GPT Image, video, audio, and LLM models.

Unified Balance

Track credits, spending, and model usage in one console.

Task Status Tracking

See whether an image task is submitted, processing, completed, or failed.

Stable Result Hosting

Generated images are re-hosted on EvoLink CDN so result links stay usable after the upstream links expire.

Grok Model Family

Grok Imagine Video 1.5

xAI video generation route: text-to-video, image-to-video, and reference-to-video in one model with 1-15s durations.

View

Grok Imagine Video

The first-generation Grok Imagine video route for text-to-video and image-to-video workflows.

View

Grok 4.6

xAI flagship text model for reasoning, coding, and agentic workflows.

View

Other image models on EvoLink

Seedream 5.0 Pro

BytePlus image route with 1K/2K output tiers, up to 10 reference images, and instruction-based editing.

View

Nano Banana 2

Google image model for high-quality generation and flexible creative workflows.

View

GPT Image 2

OpenAI image route for prompt, reference, and editing workflows.

View

Qwen Image Edit

Image editing route for direct transformations and localized creative changes.

View

FAQ

What is the exact Grok Imagine Image 2.0 model ID?

Use grok-imagine-image-2.0 for both text-to-image generation and editing with 1-3 reference images. You do not need a separate editing model ID.

How much does Grok Imagine Image 2.0 cost?

Pricing is a matrix of resolution and quality: 1K Low is the base rate, 1K Medium and 2K Low are 1.5x, and 2K Medium is 2x. The output rate is multiplied by n, and each input image adds 0.25x base once per request.

Can I preview before integrating the API?

Yes. Use the Playground to test output quality, estimate credits, and inspect the request JSON before wiring it into your product.

What is the difference between quality and resolution?

quality (low/medium) controls generation effort - low takes about 10s, medium 10-75s with better detail. resolution (1k/2k) controls output pixels. They are independent parameters and both affect the price.

How do I use it for image editing?

Pass 1-3 image URLs in image_urls together with the prompt. The model switches to editing mode automatically. With multiple images, reference each one in the prompt as <IMAGE_0>, <IMAGE_1>, <IMAGE_2>.

Can I generate multiple images with n?

Yes. n can be 1-10 in a single request. The output rate is multiplied by n, while input image fees are charged only once per request.

Are input images billed?

Yes. Each input image in image_urls adds 0.25x the base rate, charged once per request regardless of n. Only public http(s) URLs are accepted - base64 uploads are rejected.

Can I set custom pixel dimensions?

No. size accepts 13 aspect-ratio presets plus auto. Custom WIDTHxHEIGHT values are not supported; resolution is controlled separately with the 1k/2k parameter.

What if a generation fails?

Failed tasks are not charged - the full pre-authorized amount is refunded, including upstream rejections, content moderation blocks, and timeouts.

Where do I go after topping up?

Return to the Playground for more tests, or create an API key and use /v1/images/generations with model grok-imagine-image-2.0.

API Reference

Select endpoint

Endpoints

Authentication

All APIs require Bearer Token authentication.

Header

Authorization: 
Bearer YOUR_API_KEY

Get API Key

POST

/v1/images/generations

Generate Image

Grok Imagine Image 2.0 is xAI's image generation and editing model — text-to-image and image editing share the same model name. Omit image_urls for text-to-image; pass 1-3 reference images and it automatically switches to image editing, no model change needed.

Asynchronous processing mode, use the returned task ID to .

Generated image links are valid for 24 hours, please save them promptly.

Request Parameters

modelstringRequiredDefault: grok-imagine-image-2.0

Image generation model name. Text-to-image and image editing share this model name; the mode switches automatically depending on whether image_urls is provided.

Value	Description
grok-imagine-image-2.0	Grok Imagine Image 2.0 model

Examplegrok-imagine-image-2.0

promptstringRequired

Prompt describing the image you want to generate, or how to edit the reference images you provide.

Notes

Multi-image reference syntax: use <IMAGE_0>, <IMAGE_1>, <IMAGE_2> in the prompt to refer to the 1st, 2nd and 3rd reference image respectively
Indexes start at 0 and map one-to-one to the order of the image_urls array
Example: Place the person from <IMAGE_0> into the scene of <IMAGE_1>

ExampleCyberpunk Tokyo street at night, neon lights reflecting on the wet pavement

image_urlsarrayOptional

Reference image URL list for image-to-image and image editing functions.

Notes

Number of input images per request: 0~3 (omitted = text-to-image, 1~3 = image editing)
Only publicly accessible http / https image URLs are supported; base64 and data URLs are not supported
Supported file formats: .jpeg, .jpg, .png, .webp
Image URLs must be directly accessible by the server, or directly download when accessed (typically ending with image file extensions such as .png, .jpg)
In image editing scenarios the reference images incur an additional charge, counted once per request and not multiplied by n

Example["https://example.com/person.png", "https://example.com/scene.png"]

sizestringOptionalDefault: auto

Aspect ratio of the generated image, defaults to auto.

Value	Description
auto	The model decides the ratio itself; omitting this parameter is equivalent to auto (output is usually portrait)
1:1	Square
4:3 / 3:4	Classic landscape / portrait
3:2 / 2:3	Standard landscape / portrait
16:9 / 9:16	Widescreen / mobile portrait
2:1 / 1:2	Ultra-wide / ultra-tall
19.5:9 / 9:19.5	Full-screen phone landscape / portrait
20:9 / 9:20	Ultra-wide landscape / portrait

Notes

Values outside the 13 supported ratios are not supported; custom WIDTHxHEIGHT pixel sizes are not accepted

Example16:9

resolutionstringOptionalDefault: 1K

Pixel tier of the output image, defaults to 1K; supports the 1K and 2K tiers.

Value	Description
1K	Standard resolution (default)
2K	Higher resolution

Notes

This model does not support 4K
Values are case-insensitive

Example1K

qualitystringOptionalDefault: medium

Generation quality tier, controls how deeply the model thinks, defaults to medium.

Value	Description
low	Faster output, lower cost
medium	Better image quality and detail

Notes

This model only supports the low / medium tiers; other values such as high are not supported
quality (quality tier) and resolution (pixel tier) are independent and can be combined freely
Values are case-insensitive

Examplemedium

nintegerOptionalDefault: 1

Number of images to generate, range 1~10, defaults to 1.

Value	Description
1-10	Any integer between 1 and 10

Notes

Each image is billed independently, cost grows linearly with n
The additional charge for reference images is counted once per request and is not multiplied by n
When the task completes, results returns n independent image links

Example1

callback_urlstringOptional

HTTPS callback address after task completion.

Notes

Triggered when task is completed, failed, or cancelled; sent after billing confirmation
HTTPS only; callbacks to internal IP addresses are prohibited; max length 2048 chars
Timeout: 10s, max 3 retries on failure (after 1s / 2s / 4s)
Callback body format is consistent with the task query API response; a 2xx response is considered successful, other status codes trigger a retry

Examplehttps://your-domain.com/webhooks/image-task-completed

Examples

Request Example (Text to Image)

{
  "model": "grok-imagine-image-2.0",
  "prompt": "Cyberpunk Tokyo street at night, neon lights reflecting on the wet pavement",
  "size": "16:9",
  "resolution": "2K",
  "quality": "medium"
}

Request Example (Multi-image Editing)

{
  "model": "grok-imagine-image-2.0",
  "prompt": "Place the person from <IMAGE_0> into the scene of <IMAGE_1>, keeping the lighting consistent",
  "size": "16:9",
  "resolution": "1K",
  "quality": "medium",
  "image_urls": [
    "https://example.com/person.png",
    "https://example.com/scene.png"
  ]
}

Request Example (Batch Generation, Fast Tier)

{
  "model": "grok-imagine-image-2.0",
  "prompt": "A cute robot in pixel art style",
  "size": "1:1",
  "resolution": "1K",
  "quality": "low",
  "n": 4
}

Response Example

{
  "created": 1757156493,
  "id": "task-unified-1757156493-imcg5zqt",
  "model": "grok-imagine-image-2.0",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 100
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 3.06,
    "user_group": "default"
  }
}

Completed Usage Example

{
  "id": "task-unified-1757156493-imcg5zqt",
  "object": "image.generation.task",
  "created": 1757156493,
  "model": "grok-imagine-image-2.0",
  "status": "completed",
  "type": "image",
  "progress": 100,
  "results": ["https://cdn.evolink.ai/images/generated-image.jpg"],
  "result_data": [
    {
      "url": "https://cdn.evolink.ai/images/generated-image.jpg",
      "mime_type": "image/jpeg"
    }
  ],
  "usage": {
    "credits_used": 3.06,
    "cost": { "credits": 3.06, "cny": 0.31, "usd": 0.05 }
  }
}