Yapper API Docs

POST /api/v1/processes with "type": "image-generation". Pick any model — the API does not plan-gate models. GET /api/v1/models returns the same capabilities at runtime.

Input fields

Field	Type	Required	Description
`prompt`	`string`	yes	What to generate.
`aspectRatio`	`string`	no	One of the model's aspect ratios, e.g. "16:9". Use "adaptive" when advertised to follow the primary image/video reference.
`imageResolution`	`string`	no	One of the model's resolutions, e.g. "1080" or "4k".
`referenceImageUrls`	`string[]`	no	Plain https image URLs to guide/edit with. External URLs are imported into your asset library first (validated + stored); Yapper asset URLs pass through untouched.
`referenceImages`	`({assetId} \| {url})[]`	no	Image references. Send either {assetId} for a Yapper asset or {url} for a public URL to import. Legacy {docId, url} objects remain accepted.
`promptUpsampling`	`boolean`	no	Let the provider expand the prompt before generating.
`disableAutoRetries`	`boolean`	no	Disable automatic same-model retries. Defaults to false, so automatic retries are enabled.
`maskUrl`	`string`	no	Inpainting mask URL (white = regenerate) for edit models.

Referencing media: referenceImageUrls takes plain https image URLs. The normalized referenceImages, referenceVideos, and referenceAudios fields accept either {assetId} for an existing Yapper asset or {url} for public media, which is imported automatically. Provider-native asset:// URIs are internal and are not accepted here. Legacy {docId, url} objects remain accepted for backwards compatibility.

Example

Add "dryRun": true to get the exact credit cost without starting, and always send an Idempotency-Key header on real starts.

POST /api/v1/processes
{
  "type": "image-generation",
  "model": "grok-imagine-image",
  "input": {
    "prompt": "A polished product photo of a stainless steel water bottle",
    "aspectRatio": "1:1",
    "imageResolution": "1080"
  }
}

Models at a glance

Credits are per generated output; ranges span the supported resolutions/lengths (exact prices in each model's section).

Model	Company	Credits	Resolutions	Max ref images
`nano-banana-pro`	google	21–36	720, 1080, 2k, 4k	14
`nano-banana-2`	google	11–23	720, 1080, 2k, 4k	14
`nano-banana-2-lite`	google	9	1080	14
`gemini-image`	google	8–10	720, 1080	3
`gpt-image-2`	openai	10–20	720, 1080, 2k, 4k	8
`seedream-v4.5`	bytedance	8–20	1080, 2k, 4k	4
`seedream-v5.0-pro`	bytedance	42	1080, 2k, 3k	10
`seedream-v5.0-lite`	bytedance	20	2k, 4k	14
`grok-imagine-image-2.0`	xai	13–18	1080, 2k	3
`grok-imagine-image`	xai	6	1080, 2k	4
`flux-2-pro`	black-forest-labs	10–20	1080, 2k	4
`gpt-image-2-high`	openai	30–80	720, 1080, 2k, 4k	8

Nano Banana Pro (nano-banana-pro)

Google's advanced image generation and editing model.


Credits	720: 21 · 1080: 21 · 2k: 21 · 4k: 36
Aspect ratios	auto, 1:1, 16:9, 21:9, 9:16, 3:4, 4:3 (default 1:1)
Resolutions	720, 1080, 2k, 4k
Reference images	up to 14

Nano Banana 2 (nano-banana-2)

Google's latest and leading image model.


Credits	720: 11 · 1080: 12 · 2k: 18 · 4k: 23
Aspect ratios	auto, 1:1, 16:9, 9:16, 3:4, 4:3 (default 1:1)
Resolutions	720, 1080, 2k, 4k
Reference images	up to 14

Nano Banana 2 Lite (nano-banana-2-lite)

Google's fastest and cheapest image model.


Credits	1080: 9
Aspect ratios	auto, 1:1, 16:9, 9:16, 3:4, 4:3 (default 1:1)
Resolutions	1080
Reference images	up to 14

Nano Banana (gemini-image)

Google's legacy image model with quick generation times.


Credits	720: 8 · 1080: 10
Aspect ratios	auto, 1:1, 16:9, 9:16, 3:4, 4:3 (default 16:9)
Resolutions	720, 1080
Reference images	up to 3

GPT Image 2 (gpt-image-2)

Strong image generation and editing model that's especially good at text and typography, with precise instruction following and balanced cost.


Credits	720: 10 · 1080: 10 · 2k: 10 · 4k: 20
Aspect ratios	auto, 1:1, 16:9, 21:9, 9:16, 3:4, 4:3, 3:2, 2:3 (default 4:3)
Resolutions	720, 1080, 2k, 4k
Reference images	up to 8

Seedream-V4.5 (seedream-v4.5)

Bytedance's advanced image generation model.


Credits	1080: 8 · 2k: 10 · 4k: 20
Aspect ratios	auto, 1:1, 16:9, 9:16, 3:4, 4:3 (default 16:9)
Resolutions	1080, 2k, 4k
Reference images	up to 4

Seedream-V5.0 Pro (seedream-v5.0-pro)

Bytedance's flagship Seedream image generation and editing model.


Credits	1080: 42 · 2k: 42 · 3k: 42
Aspect ratios	auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 (default 1:1)
Resolutions	1080, 2k, 3k
Reference images	up to 10

Seedream-V5.0 Lite (seedream-v5.0-lite)

Bytedance's fast next-generation Seedream image generation and editing model.


Credits	2k: 20 · 4k: 20
Aspect ratios	auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 (default 1:1)
Resolutions	2k, 4k
Reference images	up to 14

Grok Image 2 (grok-imagine-image-2.0)

xAI's latest image generation and editing model, with stronger typography, layout, and instruction following.


Credits	1080: 13 · 2k: 18
Aspect ratios	auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2 (default 1:1)
Resolutions	1080, 2k
Reference images	up to 3
Max prompt length	8000

Grok Image (grok-imagine-image)

xAI's image generation and editing model.


Credits	1080: 6 · 2k: 6
Aspect ratios	auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 (default 1:1)
Resolutions	1080, 2k
Reference images	up to 4

Flux.2 Pro (flux-2-pro)

Flux's advanced image generation model.


Credits	1080: 10 · 2k: 20
Aspect ratios	auto, 1:1, 16:9, 9:16, 3:4, 4:3, 2:3, 3:2 (default 16:9)
Resolutions	1080, 2k
Reference images	up to 4

GPT Image 2 High Effort (gpt-image-2-high)

High-effort GPT Image 2 variant for stronger fidelity and more deliberate final outputs.


Credits	720: 30 · 1080: 30 · 2k: 50 · 4k: 80
Aspect ratios	auto, 1:1, 16:9, 21:9, 9:16, 3:4, 4:3, 3:2, 2:3 (default 4:3)
Resolutions	720, 1080, 2k, 4k
Reference images	up to 8

Image generation