Model API'si

Cosmos 3 Super Image

Cosmos 3 Super Image ile sahne tarifinden görsel oluştur.

Model kimliği

Her istekte bunu kullan

nvidia/cosmos-3-super/text-to-image

Çalıştır

Girdiye ücret teklifi al, bu teklifle üretimi başlat, ardından işin durumunu sorgula. Önce RAYWAKE_API_KEY değişkenini ayarla; ayrıntılar için Kimlik doğrulama sayfasına bak.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nvidia/cosmos-3-super/text-to-image",
  "input": {
    "prompt": "A red ceramic cup on a wooden table, soft morning light"
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "nvidia/cosmos-3-super/text-to-image", "quote_id": "QUOTE_ID", "input": {"prompt":"A red ceramic cup on a wooden table, soft morning light"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Girdi

nvidia/cosmos-3-super/text-to-image girdi alanları
Alan	Tür	Açıklama
`prompt`zorunlu	string	Text prompt describing the image to generate.
`negative_prompt`	string	Content to steer the generation away from (colors, objects, artifacts).
`enable_prompt_expansion`	boolean	Expand the prompt with OpenRouter before image generation. When enabled, the prompt is rewritten into the dense structured-JSON format Cosmos3 was trained on; generation falls back to the raw prompt if expansion fails. Varsayılan: `false`
`enable_agentic_generation`	boolean	Automatically generate and compare multiple candidate images, then refine the prompt between rounds to better match the original request. This can improve prompt adherence but increases latency and billable image generations. Varsayılan: `false`
`agentic_max_iterations`	number (enum)	Maximum number of refinement rounds when agentic generation is enabled. Varsayılan: `2` Seçenekler: `2`
`agentic_samples_per_iteration`	number (enum)	Candidate images to generate and judge per agentic iteration. The best candidate advances to the next rewrite stage. Varsayılan: `2` Seçenekler: `2`
`agentic_early_stop`	boolean	Stop early when a candidate image is already a strong match for the prompt. Varsayılan: `true`
`image_size`	string (enum)	The size of the generated image. Each edge is clamped to 512-1280px (multiples of 16). Varsayılan: `square_hd` Seçenekler: `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`
`num_inference_steps`	number (enum)	Number of denoising steps. More steps yield higher quality but take longer. Varsayılan: `28` Seçenekler: `28`
`guidance_scale`	number	Classifier-free guidance scale. Higher values increase prompt adherence at the cost of diversity. Varsayılan: `4`
`num_images`	integer	The number of images to generate. Varsayılan: `1`
`seed`	integer	The same seed and prompt given to the same model version will produce the same image every time.
`sync_mode`	boolean	If `True`, the image is returned as a data URI and the output data won't be available in the request history. Varsayılan: `false`
`output_format`	string (enum)	The format of the generated image. Varsayılan: `jpeg` Seçenekler: `jpeg`, `png`

Çıktı

Başarılı bir iş, sonuçlarını outputs altında listeler; dosyalar bizim tarafımızda saklanır. Tüm alanlar için İşler sayfasına bak.

İş yanıtından bir bölüm

"outputs": [
  { "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]

Fiyatlandırma

1 görsel$0,07/ görsel

Girdinin kesin ücreti ücret teklifinden gelir. Bakiye nasıl kesinleşir?