Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.nano-gpt.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Use GET /api/v1/video-models to discover the currently available video models. Do not hardcode video model capabilities in your client; supported settings and availability can change. This endpoint is cacheable. Refresh it periodically and treat new fields as additive.

​
Endpoint

GET https://nano-gpt.com/api/v1/video-models

​
Authentication

Authentication is optional.
  • Authorization: Bearer YOUR_API_KEY
  • x-api-key: YOUR_API_KEY

​
Query Parameters

ParameterTypeDefaultDescription
detailedbooleantrueInclude names, descriptions, pricing, capabilities, and supported parameters.

​
Response

{
  "object": "list",
  "data": [
    {
      "id": "video-model-id",
      "object": "model",
      "name": "Display name",
      "description": "Model description",
      "architecture": {
        "modality": "video",
        "input_modalities": ["text", "image"],
        "output_modalities": ["video"]
      },
      "pricing": {
        "currency": "USD"
      },
      "capabilities": {
        "video_generation": true,
        "text_to_video": true,
        "image_to_video": true,
        "audio_generation": false
      },
      "supported_parameters": {}
    }
  ],
  "meta": {
    "count": 1,
    "generated_at": "2026-05-07T12:00:00.000Z"
  }
}

​
Supported Parameters

Supported parameters vary by model. Common examples include:
  • duration
  • aspect_ratio
  • resolution
  • image input support
  • audio generation support
  • video extension support
  • video recovery support
  • prompt enhancement or safety controls
Use the model’s supported_parameters and capabilities objects to decide which controls to show and which request fields to send.

​
Example

curl "https://nano-gpt.com/api/v1/video-models?detailed=true"

​
Notes

  • Use this endpoint instead of hardcoding media model capabilities.
  • The response is cacheable, but model availability can change.
  • Pricing structures vary by model, for example per generation, per second, duration tier, resolution tier, or feature-specific pricing.