Models

Every image and video model on genkiln: IDs, prices in credits and USD, and the input parameters each model accepts.

Prices are in credits; 1 credit = US$0.001. The price list is the same for every account and is fixed on our side. The cost of each task is returned as cost_credits when you create it.

Catalog

ModelMakerTypeCredits
Veo 3.1 Liteveo-3.1-liteGoogleVideo720p: 195 ($0.20) / video · 1080p: 230 ($0.23) / video
Veo 3.1 Fastveo-3.1-fastGoogleVideo720p: 390 ($0.39) / video · 1080p: 425 ($0.42) / video
Seedance 2.0 Fastseedance-2.0-fastByteDanceVideo480p: 77 ($0.077) / second · 720p: 161 ($0.16) / second
Kling 3.0kling-3.0KuaishouVideo720p: 91 ($0.091) / second · 720p · audio: 130 ($0.13) / second · 1080p: 117 ($0.12) / second · 1080p · audio: 176 ($0.18) / second
Nano Banana 2nano-banana-2GoogleImage1K: 52 ($0.052) / image · 2K: 78 ($0.078) / image · 4K: 117 ($0.12) / image
Nano Banana Pronano-banana-proGoogleImage1K / 2K: 117 ($0.12) / image · 4K: 156 ($0.16) / image
GPT Image 2gpt-image-2OpenAIImage1K: 39 ($0.039) / image · 2K: 65 ($0.065) / image · 4K: 104 ($0.10) / image

List models from the API

GET /v1/models returns every model that is currently available, with its prices and the JSON Schema of its input. No API key is needed.

curl https://genkiln.com/v1/models
JSON
{
  "object": "list",
  "data": [
    {
      "id": "nano-banana-2",
      "object": "model",
      "name": "Nano Banana 2",
      "vendor": "Google",
      "media_type": "image",
      "modes": ["text-to-image", "image-to-image"],
      "description": "Google's fast image model for generation and editing ...",
      "available": true,
      "pricing": [
        { "label": "1K", "unit": "image", "credits": 52, "usd": 0.052 },
        { "label": "2K", "unit": "image", "credits": 78, "usd": 0.078 },
        { "label": "4K", "unit": "image", "credits": 117, "usd": 0.117 }
      ],
      "input_schema": {
        "type": "object",
        "properties": {
          "prompt": { "type": "string", "minLength": 1, "maxLength": 20000 },
          "...": {}
        },
        "required": ["prompt"],
        "additionalProperties": false
      }
    }
  ]
}

GET /v1/models/{id} returns one model. It also answers for a model that is temporarily unavailable, with "available": false; creating a task for it returns 422 model_unavailable until it is back. An unknown ID returns 404 not_found.

pricing[].unit is image, video (flat price per clip) or second (multiply by duration).

Parameters by model

Fields not listed are rejected. image_urls switches a model from text-to-image or text-to-video to image-to-image or image-to-video; for video models, pass 1 URL for the first frame or 2 for the first and last frame.

For gpt-image-2, some aspect ratios are not available at higher resolutions: at 2K, 5:4, 4:5, 3:1, 1:3 and 9:21 are rejected; at 4K, 3:1, 1:3 and 9:21 are rejected.

Veo 3.1 Lite veo-3.1-lite

Google's most affordable Veo 3.1 tier: 4–8 second clips with native audio from a prompt or a first/last frame. Model page →

Modes: text-to-video, image-to-video

OptionCreditsUSD
720p195 / video$0.20 / video
1080p230 / video$0.23 / video
ParameterTypeRequiredAllowed valuesDefault
promptstringYes1–5000 characters—
image_urlsarray<string>No1–2 items, public https URLs—
durationnumberNo4 6 88
resolutionstringNo720p 1080p720p
aspect_ratiostringNo16:9 9:16 auto16:9

Veo 3.1 Fast veo-3.1-fast

Veo 3.1 Fast: cinematic 4–8 second video with synchronized audio, tuned for speed. Text-to-video or first/last frame. Model page →

Modes: text-to-video, image-to-video

OptionCreditsUSD
720p390 / video$0.39 / video
1080p425 / video$0.42 / video
ParameterTypeRequiredAllowed valuesDefault
promptstringYes1–5000 characters—
image_urlsarray<string>No1–2 items, public https URLs—
durationnumberNo4 6 88
resolutionstringNo720p 1080p720p
aspect_ratiostringNo16:9 9:16 auto16:9

Seedance 2.0 Fast seedance-2.0-fast

Seedance 2.0 Fast: 4–15 second clips at 480p or 720p with optional audio, billed per second of output. Model page →

Modes: text-to-video, image-to-video

OptionCreditsUSD
480p77 / second$0.077 / second
720p161 / second$0.16 / second
ParameterTypeRequiredAllowed valuesDefault
promptstringYes3–20000 characters—
image_urlsarray<string>No1–2 items, public https URLs—
durationintegerNo4–155
resolutionstringNo480p 720p720p
aspect_ratiostringNo16:9 9:16 1:1 4:3 3:4 21:9 adaptive16:9
generate_audiobooleanNo—true

Kling 3.0 kling-3.0

Kling 3.0: 3–15 second video at 720p or 1080p, with optional generated sound, billed per second. Model page →

Modes: text-to-video, image-to-video

OptionCreditsUSD
720p91 / second$0.091 / second
720p · audio130 / second$0.13 / second
1080p117 / second$0.12 / second
1080p · audio176 / second$0.18 / second
ParameterTypeRequiredAllowed valuesDefault
promptstringYes1–2500 characters—
image_urlsarray<string>No1–2 items, public https URLs—
durationintegerNo3–155
resolutionstringNo720p 1080p720p
aspect_ratiostringNo16:9 9:16 1:116:9
generate_audiobooleanNo—false

Nano Banana 2 nano-banana-2

Google's fast image model for generation and editing with up to 10 reference images, 1K to 4K output. Model page →

Modes: text-to-image, image-to-image

OptionCreditsUSD
1K52 / image$0.052 / image
2K78 / image$0.078 / image
4K117 / image$0.12 / image
ParameterTypeRequiredAllowed valuesDefault
promptstringYes1–20000 characters—
image_urlsarray<string>No0–10 items, public https URLs—
aspect_ratiostringNoauto 1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9 21:9 1:4 4:1 1:8 8:1auto
resolutionstringNo1K 2K 4K1K
output_formatstringNopng jpgpng

Nano Banana Pro nano-banana-pro

Google's highest-quality image model: sharp text rendering, multi-image composition (up to 8 references), 1K/2K/4K. Model page →

Modes: text-to-image, image-to-image

OptionCreditsUSD
1K / 2K117 / image$0.12 / image
4K156 / image$0.16 / image
ParameterTypeRequiredAllowed valuesDefault
promptstringYes1–20000 characters—
image_urlsarray<string>No0–8 items, public https URLs—
aspect_ratiostringNoauto 1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9 21:91:1
resolutionstringNo1K 2K 4K1K
output_formatstringNopng jpgpng

GPT Image 2 gpt-image-2

OpenAI's GPT Image 2: prompt-faithful generation and editing with up to 16 input images, 1K to 4K. Model page →

Modes: text-to-image, image-to-image

OptionCreditsUSD
1K39 / image$0.039 / image
2K65 / image$0.065 / image
4K104 / image$0.10 / image
ParameterTypeRequiredAllowed valuesDefault
promptstringYes1–20000 characters—
image_urlsarray<string>No0–16 items, public https URLs—
aspect_ratiostringNoauto 1:1 3:2 2:3 4:3 3:4 5:4 4:5 16:9 9:16 2:1 1:2 3:1 1:3 21:9 9:21auto
resolutionstringNo1K 2K 4K1K