AnyInt Docs

Models

Use this section to choose the right model family, request shape, and output modality before you hardcode a model ID.

Use this section before you hardcode a model ID or copy a provider example into production. Model choice in AnyInt includes three separate decisions: the compatibility family, the input/output modality, and the operational pattern for sync, streaming, or task-based work.

Choose by question

QuestionPage
Which model or compatibility family should I use?Models
Which modalities does AnyInt expose?Overview
How do I send image input to a model?Images Input
How do I generate images?Image Generation
How do I generate videos or poll video tasks?Video Generation
StepDecisionWhere to confirm
1Which account and environment will run this workload?Your deployment configuration and AnyInt dashboard
2Which model IDs are actually available?Models API
3Which compatibility family does your client already speak?API Reference
4Does the request need text, image, video, or music output?Overview
5Is the response sync, streaming, or task-based?The API page for the selected route
6What fallback should run if the primary path fails?Model Fallbacks

Route family quick map

WorkloadStart withNotes
Text chat, summarization, extraction, or coding-agent requestsOpenAI-compatible APIFastest first integration for most clients
Claude-style messages or image understanding with content blocksAnthropic-compatible APIUse Anthropic headers and content block request shapes
Gemini-native generation, image models, or Gemini function declarationsGemini-compatible APIUse contents[].parts[]; do not send OpenAI messages to Gemini routes
Prompt-driven image or video generationMedia APIImage responses can be sync; video is usually task-based
Songs, covers, lyrics, stems, or music videosAI Music APITreat creation as an async workflow with polling or callbacks

Keep the API contract separate

This section helps you make product and workload choices. For the exact model discovery endpoint, use Models API. The current verified model list route is GET /openai/v1/models.

Do not infer support from a model name alone. A model can support text in one API family, image input in another, and task-based media generation through a separate route. The route page defines the request body customers can rely on.

Production checklist

Before launch, confirm:

  1. The selected model ID appears in the account used by that environment.
  2. The request body matches the selected API family.
  3. Streaming, task polling, or callbacks are tested when the route requires them.
  4. A fallback model or user-facing failure path is documented.
  5. Logs do not expose API keys, private prompts, uploaded images, or generated private assets.

On this page