Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.ninjachat.ai/llms.txt

Use this file to discover all available pages before exploring further.

Which image model? Start with flux-2-klein (0.03,fastest).Use‘flux−kontext−max‘(0.03, fastest). Use `flux-kontext-max` (0.10) for best quality. Use flux-kontext-pro ($0.05) for image editing. Compare all →

​
Request

POST https://ninjachat.ai/api/v1/images
Authorization: Bearer nj_sk_YOUR_API_KEY
Content-Type: application/json

{
  "model": "flux-2-klein",
  "prompt": "A golden retriever puppy in autumn leaves, soft lighting, photorealistic",
  "size": "1920x1920",
  "n": 1
}

​
Response

{
  "model": "flux-2-klein",
  "images": [
    {
      "url": "https://cdn.example.com/generated-abc123.webp",
      "revised_prompt": "A golden retriever puppy in autumn leaves..."
    }
  ],
  "usage": { "images_generated": 1 },
  "cost": {
    "this_request": "$0.03",
    "per_image": "$0.03",
    "images": 1
  },
  "metadata": { "latency_ms": 1847, "size": "1920x1920" }
}
Your image URL is in images[0].url. Download it or display it directly.

​
Parameters

ParameterTypeRequiredDefaultDescription
promptstringYes—What you want. Be specific — style, lighting, composition. Max 4,000 chars.
modelstringNonano-banana-2Which model. See table below.
sizestringNo1920x19201920x1920 (square), 2560x1440 (landscape), 1440x2560 (portrait)
nintegerNo1Number of images (1–4). Each billed separately.
imagestringNo—Reference image URL for image-to-image. Must be public HTTPS.

​
Models

ModelIDCostSpeedBest for
FLUX Kontext Maxflux-kontext-max$0.10/img~5-15sPremium editing, max fidelity
FLUX.2 Flexflux-2-flex$0.08/img~5-10sMaximum quality generation
FLUX.1 Pro Ultraflux-1-pro-ultra$0.08/img~8-15sUltra-high resolution (4MP)
Recraft V3recraft-v3$0.08/img~5sDesign, illustrations
Google Imagen 4google-imagen-4$0.08/img~15sPhotorealism, text rendering
Nano Banana Pronano-banana-pro$0.08/img~5sProfessional assets, thinking mode
Seedreamseedream$0.08/img~8sRealistic, artistic styles
FLUX.2 Proflux-2-pro$0.05/img~3-5sBalanced quality/speed
FLUX Kontext Proflux-kontext-pro$0.05/img~5sImage editing, style transfer
Nano Banana 2nano-banana-2$0.05/img~3sBest value, text rendering
FLUX.1 Fillflux-1-fill$0.05/img~5sInpainting, outpainting
FLUX.2 Kleinflux-2-klein$0.03/img<2sFastest, batch processing
Nano Banananano-banana$0.03/img~2sFast, budget-friendly
Not ready to write code? Try this in the API Playground →

​
Full working examples

import os, requests

HEADERS = {"Authorization": f"Bearer {os.environ['NINJACHAT_API_KEY']}"}

def generate_image(prompt, model="flux-2-klein", size="1920x1920"):
    r = requests.post("https://ninjachat.ai/api/v1/images",
        headers=HEADERS,
        json={"model": model, "prompt": prompt, "size": size}
    )
    r.raise_for_status()
    return r.json()["images"][0]["url"]

# Quick draft ($0.03, <2s)
url = generate_image("A mountain landscape at sunset")
print(url)

# High quality final ($0.08, ~5-10 seconds)
url = generate_image("A mountain landscape at sunset, 8k, ultra detailed",
    model="flux-2-flex", size="2560x1440")
print(url)

​
Image-to-image

Transform an existing image by passing its URL: 
r = requests.post("https://ninjachat.ai/api/v1/images",
    headers=HEADERS,
    json={
        "model": "flux-kontext-pro",
        "prompt": "Turn this into a watercolor painting with soft colors",
        "image": "https://example.com/my-photo.jpg"  # Must be public HTTPS
    }
)
print(r.json()["images"][0]["url"])

​
Multiple images

Generate up to 4 variations in one request: 
r = requests.post("https://ninjachat.ai/api/v1/images",
    headers=HEADERS,
    json={
        "model": "recraft-v3",
        "prompt": "Logo for a coffee shop called 'Bean There', minimal vector",
        "n": 4
    }
)
for i, img in enumerate(r.json()["images"]):
    print(f"Variation {i+1}: {img['url']}")
# Cost: 4 × $0.08 = $0.32

​
Prompt tips

Be specific. Compare:
WeakStrong
dogGolden retriever puppy sitting in autumn leaves, soft golden hour lighting, shallow depth of field, photorealistic
cityCyberpunk cityscape at night, neon signs reflecting in rain puddles, aerial view, cinematic lighting, 8k
logoMinimal vector logo for a tech startup, geometric shapes, blue and white, clean lines, flat design
Include: subject + style + lighting + composition + detail level