> ## Documentation Index
> Fetch the complete documentation index at: https://docs.infery.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Generate an image
> POST /v1/images/generations — text-to-image generation.
```bash theme={null}
curl https://api.infery.ai/v1/images/generations \
-H "Authorization: Bearer $INFERY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "dall-e-3",
"prompt": "An isometric dev dashboard, neon green accents, dark theme",
"size": "1024x1024",
"n": 1
}'
```
### Sample output
*Generated with `gemini-2.5-flash-image` (Nano Banana).*
## Response formats
* `response_format: "url"` (default) → provider-hosted URL, ephemeral (\~1 hour). Download within that window if you need to keep it.
* `response_format: "b64_json"` → inline base64 PNG.
To persist the image forever, upload the decoded bytes via `POST /v1/files`.
## Supported models
See [Models catalog](/models/catalog) filtered to image modality. OpenAI (DALL·E), Google (Imagen, Gemini Image), xAI (Grok Image), Alibaba (Qwen Image), Suno-music, FLUX (self-hosted) — all accessed by slug.
## Aspect ratios and sizes
Per-model; common values: `1024x1024`, `1792x1024`, `1024x1792`, `512x512`. Check a model's `allowedParams.supported_sizes` via `GET /v1/models/{slug}`.
## OpenAPI
````yaml openapi.json POST /v1/images/generations
openapi: 3.0.0
info:
title: Infery Gateway
description: >-
Infery Inference Gateway — OpenAI-compatible API for LLMs, embeddings,
images, audio, and video
version: '1.0'
contact: {}
servers:
- url: https://api.infery.ai
description: Production
- url: http://localhost:3001
description: Local
security: []
tags: []
paths:
/v1/images/generations:
post:
tags:
- Images
summary: Create image generation
operationId: createImageGeneration
parameters: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- model
- prompt
properties:
model:
type: string
description: Model ID to use for generation
prompt:
type: string
description: Text prompt describing the image to generate
'n':
type: integer
description: >-
Number of images (model-specific max: DALL-E 3=1, Imagen=4,
GPT Image=4, DALL-E 2=10)
default: 1
size:
type: string
description: >-
Image size. DALL-E: 256x256-1792x1024. GPT Image:
1024x1024/1024x1536/1536x1024/auto
quality:
type: string
description: 'DALL-E: standard/hd. GPT Image: low/medium/high/auto'
style:
type: string
enum:
- vivid
- natural
description: DALL-E only
response_format:
type: string
enum:
- url
- b64_json
default: url
description: DALL-E only. GPT Image always returns b64_json
aspect_ratio:
type: string
description: >-
Aspect ratio (Google models, see /v1/models for allowed
values)
image_size:
type: string
description: >-
Output resolution: Imagen Standard/Ultra "1K"|"2K", Gemini 3
image "1K"|"2K"|"4K"
person_generation:
type: string
enum:
- dont_allow
- allow_adult
- allow_all
description: Person generation policy (Google models)
background:
type: string
enum:
- transparent
- opaque
- auto
description: Background type (GPT Image models only)
output_format:
type: string
enum:
- png
- webp
- jpeg
description: Output file format (GPT Image models only)
output_compression:
type: integer
description: Compression 0-100 (GPT Image, jpeg/webp only)
input_fidelity:
type: string
enum:
- high
- low
description: Match style of input images (GPT Image 1/1.5 only)
moderation:
type: string
enum:
- auto
- low
description: Content filter level (GPT Image only)
negative_prompt:
type: string
description: What to exclude from the image (Imagen 4)
seed:
type: integer
description: Seed for reproducibility (Imagen 4)
responses:
'200':
description: >-
Image generation result. When stream=true, returns SSE
(text/event-stream) with progress events, then a final chunk with
the result.
content:
application/json:
schema:
type: object
properties:
created:
type: integer
example: 1713204900
data:
type: array
items:
type: object
properties:
url:
type: string
example: /samples/image.png
description: >-
Ephemeral provider-hosted URL. Download within ~1
hour.
b64_json:
type: string
description: >-
Inline base64-encoded PNG. Present when
response_format=b64_json.
revised_prompt:
type: string
description: Prompt rewritten by the model (DALL-E 3).
example:
- url: /samples/image.png
revised_prompt: >-
Isometric illustration of a glowing neon-green AI
control panel
credits_used:
type: integer
example: 40
'400':
description: Invalid request
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponseDto'
'401':
description: Unauthorized — invalid or missing API key
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponseDto'
'404':
description: Model not found
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponseDto'
security:
- ApiKey: []
components:
schemas:
ErrorResponseDto:
type: object
properties:
error:
$ref: '#/components/schemas/ErrorDetailDto'
required:
- error
ErrorDetailDto:
type: object
properties:
message:
type: string
example: Model not found
description: Human-readable error message
type:
type: string
example: invalid_request_error
description: Error category
enum:
- invalid_request_error
- authentication_error
- permission_error
- quota_exceeded
- rate_limit_error
- server_error
code:
type: object
example: model_not_found
nullable: true
description: Stable machine-readable error code
param:
type: object
example: model
nullable: true
description: >-
Name of the request parameter that triggered the error, if
applicable
required:
- message
- type
- code
- param
securitySchemes:
ApiKey:
type: apiKey
in: header
name: Authorization
description: 'API key in format: Bearer inf_***'
````