Which endpoint should I call?
Use POST /images/generations for image models and POST /videos/generations for video models. Use POST /chat/completions for OpenAI-compatible chat requests and POST /messages for Anthropic-compatible messages.
Use public GET /models when your application needs the current visible model catalog. It does not require a Bearer API key. Catalog visibility does not guarantee that every parameter combination has a billable SKU, so use each model’s API Reference page as the request-schema source of truth.
How do I know which parameters a model supports?
Open the model page in the API Reference. Each model page defines required fields, optional fields, enum values, defaults, descriptions, and example requests.
Can I reuse existing OpenAI or Anthropic SDKs?
For chat-compatible endpoints, yes. Use POST /chat/completions for OpenAI-style integrations and POST /messages for Anthropic-style integrations. Image and video generation use LinkModel’s task-based endpoints.
How do I send a video to Gemini for understanding?
Use the Gemini-native generateContent API with a file uploaded through the Gemini file workflow. See Video understanding with Gemini for the complete upload, processing, request, and cleanup sequence.
The /v1/files/* upload workflow is only for Google Gemini models that support native fileData input. Its gs:// URI cannot be used with OpenAI, Anthropic, /chat/completions, /messages, image-generation, or video-generation endpoints.
Are the historical generation endpoints still supported?
Yes. Existing clients can continue using /image-generation, /video-generation, and their query endpoints. New integrations should use the resource-oriented routes. See Legacy API compatibility for exact mappings.
Why are some fields model-specific?
Providers expose different controls. LinkModel keeps each model schema explicit so unsupported fields are not silently accepted.
What content type should I send?
Use JSON:
