Endpoints

Images

Generate and edit images with POST /images/generations on api14, with prompts, sizes, quality settings and response formats for each model.

Try it in the playground

Generate and edit images with every image model in the catalog, GPT image, Gemini image, FLUX, Seedream, Recraft and more. The endpoint uses the OpenAI SDK's path, so client.images.generate(...) works unchanged.

POST https://api14.com/api/v1/images/generations

POST /api/v1/images is accepted as an alias. Both forward the body unchanged.

Request

Parameter	Type	Required	Description
`model`	string	yes	An image model id, e.g. `openai/gpt-5.4-image-2`.
`prompt`	string	yes	What to draw.
`n`	integer	no	Number of images. Each image is billed.
`size`	string	no	e.g. `1024x1024`, `1536x1024`. Supported sizes vary per model.
`aspect_ratio`	string	no	e.g. `16:9`, `1:1`, for models that take ratios instead of sizes.
`quality`	string	no	e.g. `low`, `medium`, `high` where supported.
`response_format`	string	no	`b64_json` or `url` where supported.
`image`	string or string[]	no	Reference image(s) as URLs or `data:` URIs for editing / image-to-image.

Model-specific options (resolutions, aspect ratios) are listed per model in GET /images/models and on each model page.

Example

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
});

const result = await client.images.generate({
  "model": "openai/gpt-5.4-image-2",
  "prompt": "A minimalist product photo of a ceramic mug on a wooden table",
  "n": 1,
  "aspect_ratio": "1:1"
});
import { writeFile } from "node:fs/promises";
await writeFile("image.png", Buffer.from(result.data[0].b64_json, "base64"));

Response

{
  "created": 1791100000,
  "data": [
    { "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..." }
  ],
  "usage": { "cost": 0.04 }
}

Some models return url instead of b64_json. Download hosted URLs promptly; they can expire.

Images through chat

Image models that also output text can be called through Chat completions with modalities:

{
  "model": "google/gemini-2.5-flash-image",
  "modalities": ["image", "text"],
  "messages": [{ "role": "user", "content": "A watercolor fox, square" }]
}

Generated images come back in choices[0].message.images[] as data URLs.

Listing image models

# Public, no API key needed
curl https://api14.com/api/v1/images/models
curl "https://api14.com/api/v1/models?category=image"

Pricing

Image models are billed at their listed price, per image or per 1M image tokens, depending on the model. The exact cost is taken from the upstream response and debited from your USD balance.

Errors

Status	Code	When
400	`model_required` / `invalid_json`	Missing `model` or malformed body.
402	`insufficient_balance`	Your USD balance is $0.
403	`model_not_allowed` / `plan_required`	Key allowlist or plan excludes the model.
404	`model_not_found`	Unknown or disabled model id.
413	`payload_too_large`	Body (e.g. inline reference images) exceeds the size limit.

Upstream validation errors (unsupported size, content policy) are passed through with their status. See Errors.