Docs/AngeMedia

Configure providers and models

A provider decides where the request is sent. A model decides what the request can do. Start with one stable provider.

ProvidersModelsCapabilities

Image providers

ProviderTypical useConsiderations
SiliconFlow / KolorsGeneral images and a stable image-to-image pathUses a fixed set of sizes
ModelScopeQwen Image, FLUX Krea and Z-Image variantsParameter support differs by model; Gateway does not force one common size
OpenAI-compatible ImageOpenAI or a private compatible endpointConfigure Base URL, key and model explicitly
PollinationsPublic or experimental image routingAvailability and size behavior can change
ByteDance SeedreamOptional image providerDepends on account and model access
Agnes ImageGeneration, reference images and editingSelect explicitly; it is not a universal default

Video providers

The main current video route is Agnes Video v2.0 for text, image and keyframe inputs. A provider should not appear in the UI until it has a real integration and validation path.

Configuration order

  1. Enter the API key and required Base URL.
  2. Run the connection test.
  3. Confirm that the account can use the selected model.
  4. Submit a minimal request using a default size.
  5. Add reference inputs and advanced parameters only after the basic request succeeds.

Default routing and explicit selection

Specify a provider or model when predictable output matters. Automatic routing can suggest a path but cannot replace model-capability checks.

When one provider fails