**Cost**: configured per generated image in `pricing.yaml` (multiplied by `n`).

Text-to-image generation. Produce one or more images from a natural-language prompt, optionally steered by reference images for style or composition. Synchronous; routes through whichever model you pick.

## What this API is for

The canonical "generate image from text" endpoint. Use it for hero art, marketing assets, agent-driven illustration, batched A/B variants. Reference images give you style/subject control without fine-tuning.

## Request

| Field | Required | Notes |
|---|---|---|
| `prompt` | yes | Text description of the image to generate. The most important field — be specific about subject, composition, lighting, and style. |
| `n` | no | Number of images to generate. Default `1`. **Credits are charged per generated image**, not per call. |
| `size` | no | Output dimensions as `WIDTHxHEIGHT`, e.g. `1024x1024`. Defaults vary by model. Common: `1024x1024`, `1536x1024`, `1024x1536`. |
| `model` | no | Model ID. Default `nano_banana_2`. Available: `nano_banana_2`, `nano_banana_pro`, `gpt_image_2_5`, `gpt_image`, `qwen_image_3_pro`, `hy_image_3_5`, `seedream_5_pro`, `seedream_5_flash`, `seedream_5`, `seedream_4_5`, `recraft_v4`, `flux_3`, `flux_2_pro`, `flux_2_max`, `ideogram_v4`. Each has its own aesthetic / strength — see the table below. |
| `quality` | no | For `gpt_image`, use `low`, `medium`, `high`, or `auto`. For `gpt_image_2_5` (including Flare and Sunburst), `xhigh` and `max` are also supported. Omitted quality or `auto` uses the medium billing bucket. For non-GPT models, this field may carry the resolution tier (for example `1K` or `2K`). |
| `background` | no | Background mode (model-dependent). For `gpt_image`: `transparent` / `opaque` / `auto`. |
| `reference_images` | no | Array of public image URLs to steer the generation. Most models accept up to a handful — semantics vary (style ref vs. subject ref). `flux_3` accepts up to 10 reference images. |

### Model cheat-sheet

| Model | Strength |
|---|---|
| `nano_banana_2` (default) | Fast, general-purpose, good prompt adherence. |
| `nano_banana_pro` | Higher fidelity at higher latency. |
| `gpt_image_2_5` | GPT Image 2.5 with Flare and Sunburst variants; supports low, medium, high, xhigh, max, and auto quality. |
| `gpt_image` | Best for text inside images and structured layouts. Supports `quality` and `background`. |
| `qwen_image_3_pro` | Detailed layouts, multilingual text rendering, dense information-rich images, and 512/1K/2K outputs. No 4K. `image_generate` accepts up to 3 references; `image_to_image` accepts up to 2. |
| `hy_image_3_5` | Photorealistic generation and reference-guided editing; 1K/2K outputs and up to 5 input images. |
| `seedream_5_pro` | Precision generation and editing with advanced visual reasoning; 1K/2K outputs and up to 10 references. |
| `seedream_5_flash` | Fast, low-cost generation and editing; 1K/2K outputs at one price and up to 10 references. |
| `seedream_5` / `seedream_4_5` | Cinematic, photographic. |
| `flux_3` | Native 1K/2K/4K generation, precise prompt following, and up to 10 references. |
| `flux_2_pro` / `flux_2_max` | High-quality, very precise prompt following. |
| `recraft_v4` | Vector-friendly art / illustration. |
| `ideogram_v4` | Latest Ideogram typography, posters, logos. |

## Response

Shared `ImageUrlListSuccess` — `data.image_urls` is an array of CDN URLs, length `n`.

## Billing

**Credits charged per generated image**, not per call. For `n = 4`, the configured per-image model price is multiplied by 4. Check `GET /v2/open/limits` for the live per-operation price table and `GET /v2/open/usage` for charged calls. Uses the unified Codia Open API balance.

## Errors

- `400` — missing/empty `prompt`, invalid `size` format, unknown `model`, too many `reference_images`.
- `401` / `403` — auth.
- `402` — credits exhausted.
- `429` — rate limit.
- `500` — internal; safe to retry.

> **Sync vs. async**
> This synchronous endpoint returns the result inline. When `n > 1` the call generates images concurrently and may still approach HTTP timeouts; prefer `POST /v2/open/tasks` with `operation=image_generate` for batch jobs (and for webhook delivery / retry semantics). Inputs and per-image credit cost are identical.

Optional user-supplied key (up to 255 chars). When set, a successful (2xx) response is cached for 7 days. A retry with the same key + identical request body returns the cached response (no extra credit charged); a retry with the same key but a different body returns 409. Use to make POST safe to retry on network failures.

Idempotency-Key

Text description of the image to generate

prompt

Number of images to generate. Credits are charged per generated image.

Output image dimensions as `WIDTHxHEIGHT`. Common sizes: `1024x1024`, `1536x1024`, `1024x1536`. FLUX 2 Pro/Max also accept 1K/2K size presets. Oversized requests, including 4K, are reduced to at most approximately 4MP (2048x2048 for square images); native 4K output is not supported. Billing uses the adjusted output area: up to 1,048,576 pixels in total uses the 1K price, and larger outputs use the 2K price. An explicit size takes precedence over a resolution hint in quality.

size

Model that generates the image. Defaults to `nano_banana_2`. Supported models match Codia Studio for text-to-image generation. Credits are configured in `pricing.yaml` and returned by `GET /v2/open/limits`.

| Model | Best for |
| --- | --- |
| `nano_banana_2` | Fast everyday generation (Gemini 3.1 Flash). |
| `nano_banana_pro` | Studio-quality 4K visuals with advanced reasoning (Gemini 3 Pro). |
| `gpt_image_2_5` | GPT Image 2.5 with Flare and Sunburst variants; supports low, medium, high, xhigh, max, and auto quality. |
| `gpt_image` | Crisp in-image text, high-fidelity references, flexible sizes. Supports `quality` (`low`/`medium`/`high`/`auto`) and `background` (`transparent`/`opaque`/`auto`). |
| `qwen_image_3_pro` | Detailed layouts, multilingual text rendering, dense information-rich images, and 512/1K/2K outputs. No 4K. `image_generate` accepts up to 3 references; `image_to_image` accepts up to 2. |
| `hy_image_3_5` | Photorealistic generation and reference-guided editing at 1K/2K. No 4K. Accepts up to 5 input images per request. |
| `seedream_5_pro` | Precision generation with advanced visual reasoning; supports 1K/2K outputs and up to 10 reference images. |
| `seedream_5_flash` | Fast, low-cost generation; supports 1K/2K outputs at one price and up to 10 reference images. |
| `seedream_5` | Photorealistic imagery with fine detail. Sizes are 1920-based, e.g. `1920x1080`. |
| `seedream_4_5` | Reliable photorealism, great for portraits. Sizes are 1920-based. |
| `recraft_v4` | Illustrations, icons, and vector-style art with precise style control. |
| `flux_3` | Native 1K/2K/4K generation with precise prompt following and up to 10 references. |
| `flux_2_pro` | High-quality FLUX generation by Black Forest Labs. |
| `flux_2_max` | Maximum-quality FLUX tier for premium results. |
| `ideogram_v4` | Latest Ideogram typography and creative compositions. |

model

For `gpt_image`, use `low`, `medium`, `high`, or `auto`. For `gpt_image_2_5` (including Flare and Sunburst), `xhigh` and `max` are also supported. Omitted quality or `auto` uses the medium billing bucket. For non-GPT models, this field may carry the resolution tier (for example `1K` or `2K`).

quality

Background mode (model-dependent). For GPT Image 2 and 2.5: `transparent`, `opaque`, or `auto`.

background

Reference image URLs for style guidance (model-dependent)

reference_images

code

message

image_urls

data

The request body is malformed or missing required parameters

The API key is missing, invalid, or revoked

Account balance is insufficient or subscription has expired

Account does not have access to this endpoint

Idempotency-Key reused with a different request body.

Rate limited. Wait for the number of seconds in the `Retry-After` header before retrying.

An unexpected error occurred on the server

Generates images from a text prompt, optionally guided by reference images, across a choice of models.

Generate Image

Input

Output

Related APIs