Image generation

GPT Image

Nano Banana

FLUX

Seedream

Citrus drink campaign with sculptural studio lighting

Summer drink campaign beside a turquoise pool

Drink campaign against a dramatic volcanic landscape

Generate an image

Send a prompt. Get an image URL.

POST /api/v1/images/generations

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

Response

{
  "created": 1787529600,
  "model": "flux-2-klein",
  "provider": "...",
  "data": [{"url": "https://cdn.../generated-abc123.webp", "revised_prompt": "..."}],
  "usage": {"images_generated": 1},
  "cost_usd": 0.014,
  "request_id": "req_...",
  "routing": {"provider_attempts": ["..."], "retries": 0}
}

With default durable storage, your image URL is in data[0].url. The response also includes cost and request details.

Parameters

Parameter	Default	Description
`prompt`	required	Be specific — subject, style, lighting, composition. Max 4,000 chars.
`model`	`nano-banana-2`	Choose from the model catalog.
`size`	`1920x1920`	Exactly one of `1920x1920` (square), `2560x1440` (landscape), `1440x2560` (portrait).
`n`	`1`	1–4 images; each is billed.
`image`	—	Public HTTPS reference URL for image-to-image.
`reference_images`	—	Ordered HTTPS reference URLs; up to 14, with a lower limit on some models. Use this or `image`, not both.
`storage`	`durable`	`durable` returns a permanent NinjaChat URL; `provider` skips the copy and may return a temporary URL or inline image data.
`aspect_ratio`	—	Aspect ratio for models that support it directly, e.g. `16:9`, `1:1` (Nano Banana, Imagen 4, FLUX.2 Flex).
`width`	—	Image width in pixels, 256–2048 (FLUX models only).
`height`	—	Image height in pixels, 256–2048 (FLUX models only).

size is a strict enum — 1024x1024 and other values are rejected with validation_error. Pick one of the three.

Which model?

FLUX.2 KleinBlack Forest Labs

Nano Banana 2Google

GPT Image 2OpenAI

FLUX.1 Kontext MaxBlack Forest Labs

Explore all image models and pricing →

In code

import { NinjaChat } from "@ninjachat/sdk";

const client = new NinjaChat({ apiKey: process.env.NINJACHAT_API_KEY! });
const image = await client.images.generate({
  model: "flux-2-klein",
  prompt: "A mountain landscape at sunset",
  size: "1920x1920",
});

console.log(image.data[0].url);

import os
from ninjachat import NinjaChat

client = NinjaChat(api_key=os.environ["NINJACHAT_API_KEY"])
image = client.images.generate(
    model="flux-2-klein",
    prompt="A mountain landscape at sunset",
    size="1920x1920",
)

print(image["data"][0]["url"])

Try prompts live in the Playground — every run shows the exact request. Or let an agent drive: the MCP server offers a curated selection of these models through your agent.

Get Started

Chat

Orchestration

Production

Media & search

Reference

Generate an image

Parameters

Which model?

In code

​Generate an image

​Parameters

​Which model?

​In code

Generate an image

Parameters

Which model?

In code