Grok Imagine Image 2.0 API
xAI's top-ranked image model — photoreal, bold, fast
Try Grok Imagine Image 2.0
Runs on your balance at the price shown on the button. Results are saved to your account.
Output image shape.
1K ≈ 1 MP, 2K ≈ 4 MP.
Low is faster and cheaper; medium has more detail. (Edits always run at medium.)
Create a free account with Google or email — pay only for what you generate.
Your image will appear here
Write a prompt, pick your settings and hit Run. You only pay for successful generations.
What is Grok Imagine Image 2.0?
Grok Imagine Image 2.0 from xAI generates and edits striking photoreal and stylized images at 1K or 2K, with up to 3 input images for editing.
Leaderboard quality
Grok Imagine Image 2.0 ranks among the top text-to-image models, with vivid color, realistic people and strong prompt following.
Edit with references
Give it up to three images and describe the change — new scene, outfit, style or composition.
Grok Imagine Image 2.0 pricing
Pay per image. No subscription. Failed generations are refunded automatically.
| Tier | Official price | Cheaper Gen. | You save |
|---|---|---|---|
1K · low | $0.035/img | −12% | |
1K · medium | $0.053/img | −12% | |
2K · low | $0.053/img | −12% | |
2K · medium | $0.07/img | −12% |
- Official price: xAI API list price for grok-imagine-image-2.0 (1K $0.04 low / $0.06 medium, 2K $0.06 / $0.08; $0.01 per input image). Prices verified 2026-10-16.
- Edits are billed at medium quality plus $0.01 per input image (before our discount).
Specifications
- Resolutions
- 1K · 2K
- Quality
- low · medium
- Aspect ratios
- 1:1 · 3:4 · 4:3 · 9:16 · 16:9 · 2:3 · 3:2 · 1:2 · 2:1 · 9:19.5 · 19.5:9 · 9:20 · 20:9
- Edit inputs
- Up to 3 images
Use Grok Imagine Image 2.0 via API
One request to start a job, one to fetch the result. Same shape for every model.
import os, time, requests
API = "https://cheapergen.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['CHEAPERGEN_API_KEY']}"}
# 1. Submit the job
job = requests.post(f"{API}/run/xai/grok-imagine-image/text-to-image", headers=headers, json={
"prompt": "Fashion editorial: a model in a sculptural orange coat on a salt flat at noon, harsh shadows, medium format",
"aspect_ratio": "1:1",
"resolution": "1K",
"quality": "medium"
}).json()
# 2. Poll until it finishes (or pass "webhook_url" and skip polling)
while job["status"] in ("queued", "running"):
time.sleep(3)
job = requests.get(f"{API}/generations/{job['id']}", headers=headers).json()
print(job["status"], job["output"]["images"][0]["url"] if job["status"] == "succeeded" else job["error"])Example prompts
Hit “Try it” to load a prompt into the playground above.
Grok Imagine Image 2.0 FAQ
Related models

Grok ImagineVideo 1.5
Text · Reference → Video
xAI's video model — native audio, up to 1080p and 15 s

GPT Image2.5
Text → Image · Image Edit
OpenAI's top image model — precise edits, perfect text, up to 4K

Nano Banana2.1
Text → Image · Image Edit
Google's newest Nano Banana — top-ranked quality at a quarter of Pro's price
Grok Imagine Image 2.0 is developed by xAI. Cheaper Gen. provides API access through official upstream endpoints and does not own the model. Trademarks belong to their respective owners. · Markdown · OpenAPI
