ImageGenerationRequest Type | OpenRouter TypeScript SDK | OpenRouter

The TypeScript SDK and docs are currently in beta. Report issues on GitHub.

Image generation request input

Example Usage

1 import { ImageGenerationRequest } from "@openrouter/sdk/models";
2 
3 let value: ImageGenerationRequest = {
4   model: "bytedance-seed/seedream-4.5",
5   prompt: "a red panda astronaut floating in space, studio lighting",
6 };

Fields

Field	Type	Required	Description	Example
`aspectRatio`	models.ImageGenerationRequestAspectRatio	➖	Normalized aspect ratio of the generated image. Providers clamp to their supported subset.	16:9
`background`	models.ImageGenerationRequestBackground	➖	Background treatment. `transparent` requires an output_format that supports alpha (png or webp).	auto
`inputReferences`	models.ContentPartImage[]	➖	Reference images to guide image-to-image generation, as base64 data URLs or HTTP(S) URLs.
`model`	string	✔️	The image generation model to use	bytedance-seed/seedream-4.5
`n`	number	➖	Number of images to generate (1-10). Providers that only support single-image generation reject n > 1.	1
`outputCompression`	number	➖	Compression level (0-100) for webp/jpeg output. Ignored for png and by providers without a compression knob.	100
`outputFormat`	models.ImageGenerationRequestOutputFormat	➖	Encoding of the returned image bytes.	png
`prompt`	string	✔️	Text description of the desired image	a red panda astronaut floating in space, studio lighting
`provider`	models.ImageGenerationRequestProvider	➖	Provider-specific passthrough configuration
`quality`	models.ImageGenerationRequestQuality	➖	Rendering quality. Providers without a quality knob ignore this.	high
`resolution`	models.ImageGenerationRequestResolution	➖	Normalized resolution tier of the generated image. Concrete pixel dimensions are derived per-provider.	2K
`seed`	number	➖	If specified, the generation will sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed for all providers.
`size`	string	➖	Optional. A convenience shorthand for output dimensions — pass a tier (“2K”, “4K”) or explicit pixels (“2048x2048”) and we normalize it to the right dimensions for the chosen provider. Interchangeable with resolution + aspect_ratio; use those directly for enumerated, per-model discoverable values. Conflicting size + resolution/aspect_ratio is rejected.	2K
`stream`	boolean	➖	If true, partial images are streamed as SSE events as they become available. Only supported by providers with native streaming (currently OpenAI). Non-streaming providers ignore this flag and return a buffered response.