Runway's Gen-4 Image Turbo; requires one to three reference images.
curl https://www.ninjachat.ai/api/v1/images/generations \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "runway-gen4-image-turbo", "prompt": "a red fox in a snowy forest, golden hour", "aspect_ratio": "16:9" }'Each request below is generated from what Runway Gen-4 Image Turbo serves on NinjaChat today — the same capabilities and parameters that GET /models reports — so it runs as written with your key.
This model works from an input image: pass the photo and describe the change.
# export NINJACHAT_API_KEY="nj_sk_..." (Developers → Keys)
curl https://www.ninjachat.ai/api/v1/images/generations \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "runway-gen4-image-turbo",
"prompt": "same product, now on a marble counter with morning light",
"image": "https://example.com/espresso.jpg",
"size": "1920x1920"
}'image is required on this model — a request without it is rejected with a 400 before anything is billed.storage is optional and defaults to "durable". Set it to "provider" only when lower response latency matters more than receiving a permanent NinjaChat URL.