API REFERENCE

Image generation

Generate and edit images with a unified, OpenAI-compatible endpoint that fans out to Flux, Nano-Banana, Wan and more.

One OpenAI-compatible image endpoint fans out to Flux, Nano-Banana, Wan and other providers. Send the same request shape regardless of the upstream; provider-specific options pass through and are validated against each model's capabilities.

Discover image models by listing the models endpoint and keeping the ones whose output modalities include image.

POST /v1/images/generations

Drop-in compatible with the OpenAI images.generate SDK. Provider-specific parameters live alongside the standard ones — the backend forwards what each model understands.

POSThttps://api.airforce/v1/images/generations

Image models

…· live

Common parameters

Parameter	Type	Required	Description
model	string	Required	Image model ID. Filter /v1/models by output_modalities.includes("image").
prompt	string	Required	Image description.
n	integer	Optional	Number of variations to generate per request. Capped by the model's image_caps.max_n.
size	string	Optional	OpenAI-style WxH, e.g. "1024x1024". Provider-specific values pass through.
aspect_ratio	string	Optional	Alternative to size. "16:9", "1:1", "9:16", … Validated against image_caps.aspect_ratios.
quality	string	Optional	"standard" \| "hd" (OpenAI) or model-specific labels. Validated.
response_format	string	Optional	"url" (default) or "b64_json".
seed	integer	Optional	Reproducibility seed. Same prompt + same seed = same image (where the upstream supports it).
input_images	array	Optional	[{ url? } \| { b64_json? }] for image-to-image / reference / first-frame.
sse	boolean	Optional	When true the response is sent as Server-Sent Events. The full JSON arrives in one event followed by [DONE]. Useful to keep long upstream renders from timing out at proxies.

Basic example

curl https://api.airforce/v1/images/generations \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2-dev",
    "prompt": "A cute baby sea otter floating on its back",
    "n": 1,
    "response_format": "url"
  }'

Response shape

Parameter	Type	Required	Description
created	integer	Optional	Unix timestamp.
data	array	Optional	Generated assets.
data[].url	string	Optional	Image URL when response_format is "url" (default). The image is re-hosted to a file host and the link ends in /image.jpeg; null if the re-host fails.
data[].b64_json	string	Optional	Base64-encoded image bytes when response_format is "b64_json". The format follows the upstream provider (often JPEG), not necessarily PNG.

{
  "created": 1715000000,
  "data": [{
    "url": "https://.../image.jpeg"
  }]
}

Streaming variant

Pass sse: true when proxying through middleware that has tight idle-timeouts. The response is one SSE event with the complete JSON, then [DONE].

data: {"created":1715000000,"data":[{"url":"https://.../image.jpeg"}]}

data: [DONE]

Image-to-image & reference

Models with image_caps.max_input_images > 0 accept reference images. Either pass URLs or base64-encoded data.

curl https://api.airforce/v1/images/generations \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2-dev",
    "prompt": "Same character, now in a snowy forest",
    "aspect_ratio": "16:9",
    "input_images": [
      {"url": "https://example.com/character.jpg"}
    ]
  }'

Model-specific parameters

Beyond the common parameters above, individual model families accept extras. Unknown parameters are forwarded to the upstream as-is, so any future provider-specific knob also works without an SDK update.

Flux

flux-2-klein-4b, flux-2-klein-9b, flux-2-dev

Parameter	Type	Required	Description
aspect_ratio	string	Optional	"1:1", "16:9", "9:16", "4:3", "3:4", "21:9", "9:21".
image_urls	array	Optional	Reference images for img2img mode.

Nano-Banana

nano-banana-2, nano-banana-2-search, nano-banana-pro

Parameter	Type	Required	Description
aspect_ratio	string	Optional	"1:1", "16:9", "9:16", "4:3".
resolution	string	Optional	"512", "1024", "2048".
image_urls	array	Optional	Reference images.

Suno (music via /v1/images/generations)

suno-v4.5, suno-v5 — Suno historically routes through this endpoint. Native music API at /v1/audio/music is preferred for new code.

Parameter	Type	Required	Description
custom	boolean	Optional	Switch from "auto" to fully custom mode.
instrumental	boolean	Optional	Suppress vocals.
style	string	Optional	Genre tag list, e.g. "EDM, Bass".

Discovering capabilities

Each image model exposes image_caps on /v1/models so clients can validate inputs before sending:

Parameter	Type	Required	Description
image_caps.max_n	integer	Optional	Maximum n per request.
image_caps.aspect_ratios	array	Optional	Allowed aspect_ratio values.
image_caps.qualities	array	Optional	Allowed quality values.
image_caps.max_input_images	integer	Optional	0 = text-only model. Higher = supports reference images.
image_caps.supports_url_input	boolean	Optional	Whether input_images may be passed as URLs (vs base64).
image_caps.supports_seed	boolean	Optional	Whether the model honours a seed value (most scraping-proxy upstreams ignore it).

Image pricing is not on image_caps — use the model’s price fields on /v1/models for cost.