API REFERENCE

Generazione di immagini

Genera e modifica immagini con un endpoint unificato e compatibile con OpenAI che si estende a Flux, Nano-Banana, Wan e altro ancora.

POST /v1/images/generations

Drop-in compatibile con OpenAI images.generate SDK. I parametri specifici del provider convivono insieme a quelli standard: il backend inoltra ciò che comprende ciascun modello.

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

Modelli di immagine

…· live

Parametri comuni

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.

Esempio di base

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"
  }'

Forma della risposta

Parameter	Type	Required	Description
created	integer	Optional	Unix timestamp.
data	array	Optional	Generated assets.
data[].url	string	Optional	Pre-signed CDN URL when response_format is "url".
data[].b64_json	string	Optional	Base64-encoded PNG when response_format is "b64_json".
data[].revised_prompt	string	Optional	Some models rewrite the prompt before generating; the rewritten version is returned here.

{
  "created": 1715000000,
  "data": [{
    "url": "https://cdn.api.airforce/images/abc123.png"
  }]
}

Variante in streaming

Passaggio sse: true durante l'inoltro tramite middleware con timeout di inattività ridotti. La risposta è quindi un evento SSE con il JSON completo [DONE].

data: {"created":1715000000,"data":[{"url":"https://cdn.api.airforce/images/abc123.png"}]}

data: [DONE]

Immagine per immagine e riferimento

Modelli con image_caps.max_input_images > 0 accettare immagini di riferimento. Passa URL o dati con codifica base64.

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"}
    ]
  }'

Parametri specifici del modello

Oltre ai parametri comuni di cui sopra, le singole famiglie di modelli accettano extra. I parametri sconosciuti vengono inoltrati all'upstream così come sono, quindi qualsiasi futura manopola specifica del provider funzionerà anche senza un aggiornamento dell'SDK.

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".

Alla scoperta delle capacità

Ogni modello di immagine espone image_caps SU /v1/models in modo che i client possano convalidare gli input prima di inviare:

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.sizes	array	Optional	Allowed size values when applicable.
image_caps.max_input_images	integer	Optional	0 = text-only model. Higher = supports reference images.
image_caps.price_per_image_cents	integer	Optional	Cost per generated image. Multiply by n for the total request cost.