Generation

Capabilities and models

List the capabilities Windpaint defines, the models that implement them, and each model's current price per tier.

Two read-only views of the same catalog. GET /v1/generation/capabilities is organized by capability (what you can ask for); GET /v1/generation/models is organized by model. Both return current prices, so read prices from here instead of hardcoding them.

GET /v1/generation/capabilities

Lists every capability with its input slots, accepted aspect ratios, and the models that implement it.

Scope: generation:read

Takes no parameters. Returns {"data": [Capability]}, in a fixed order.

A capability with no model yet (for example image.edit or audio.speech today) is still listed, with models: []. Submitting to it returns 422 with No model implements <capability> yet.

idstringrequired

The capability id: image.generate, video.generate, image.edit, mask.segment, media.upscale, audio.speech, video.lipsync or text.llm. Use it in POST /v1/generation/capabilities/{capability}.

descriptionstringrequired

What the capability does.

outputstring | nullrequired

The asset kind it produces: image, video, audio, mask or text. null for media.upscale, whose output kind follows its input.

prompt_requiredbooleanrequired

Whether prompt must be non-empty. false only for media.upscale and video.lipsync.

prompt_meaningstringrequired

What the prompt is for. "Instruction or description." for most capabilities; "The text to speak." for audio.speech; "What to segment, e.g. 'the product'." for mask.segment.

inputsSlot[]required

The capability’s asset input slots, with the capability’s own limits. A model can tighten these; see models[].inputs. Empty for image.generate.

aspect_ratiosstring[]required

Accepted aspect_ratio values: 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, 4:5, 5:4.

modelsOffering[]required

The models that implement this capability, in default order. When you omit model on submit, the first available one is used.

Response

200

{
  "data": [
    {
      "id": "image.generate",
      "description": "Text to image.",
      "output": "image",
      "prompt_required": true,
      "prompt_meaning": "Instruction or description.",
      "inputs": [],
      "aspect_ratios": ["1:1", "4:3", "3:4", "3:2", "2:3", "16:9", "9:16", "21:9", "4:5", "5:4"],
      "models": [
        {
          "model": "z-image-turbo",
          "description": "Z-Image Turbo. Fast, 8-step text to image.",
          "available": true,
          "prices": [
            { "resolution": "1k", "duration_s": null, "credits": "0.08" },
            { "resolution": "2k", "duration_s": null, "credits": "0.30" }
          ],
          "resolutions": ["1k", "2k"],
          "default_resolution": "1k",
          "qualities": [],
          "durations": [],
          "inputs": [],
          "licence": "Apache-2.0",
          "licence_restricted": false,
          "licence_note": null
        }
      ]
    },
    {
      "id": "video.generate",
      "description": "Prompt, optionally with a start frame and an end frame, to a video clip.",
      "output": "video",
      "prompt_required": true,
      "prompt_meaning": "Instruction or description.",
      "inputs": [
        { "name": "start_frame", "kinds": ["image"], "min": 0, "max": 1, "description": "First frame." },
        { "name": "end_frame", "kinds": ["image"], "min": 0, "max": 1, "description": "Last frame, for first/last-frame interpolation." }
      ],
      "aspect_ratios": ["1:1", "4:3", "3:4", "3:2", "2:3", "16:9", "9:16", "21:9", "4:5", "5:4"],
      "models": [
        {
          "model": "wan-2.2-i2v",
          "description": "Wan 2.2 image-to-video 14B. Start frame required. 480p, 5 s.",
          "available": true,
          "prices": [
            { "resolution": "480p", "duration_s": 5, "credits": "4.00" }
          ],
          "resolutions": ["480p"],
          "default_resolution": "480p",
          "qualities": [],
          "durations": [5],
          "inputs": [
            { "name": "start_frame", "kinds": ["image"], "min": 1, "max": 1, "description": "First frame." },
            { "name": "end_frame", "kinds": ["image"], "min": 0, "max": 0, "description": "Last frame, for first/last-frame interpolation." }
          ],
          "licence": "Apache-2.0",
          "licence_restricted": false,
          "licence_note": null
        }
      ]
    },
    {
      "id": "image.edit",
      "description": "Reference images plus instruction to image. Covers edit, inpaint (with mask), outpaint (target aspect_ratio), relight, try-on and multi-reference composition.",
      "output": "image",
      "prompt_required": true,
      "prompt_meaning": "Instruction or description.",
      "inputs": [
        { "name": "images", "kinds": ["image"], "min": 1, "max": 3, "description": "Source and reference images, in the order the prompt refers to them." },
        { "name": "mask", "kinds": ["mask"], "min": 0, "max": 1, "description": "Region to change; omit for mask-free edits." }
      ],
      "aspect_ratios": ["1:1", "4:3", "3:4", "3:2", "2:3", "16:9", "9:16", "21:9", "4:5", "5:4"],
      "models": []
    }
  ]
}

The example is trimmed to three of the eight capabilities.

GET /v1/generation/models

Lists every model with the capabilities it implements and their current prices.

Scope: generation:read

Takes no parameters. Returns {"data": [Model]}. Use the id in POST /v1/generation/models/{model} or as model in a capability request.

idstringrequired

The model id, for example z-image-turbo or wan-2.2-i2v. Ids are stable slugs; there is no version pinning.

capabilitiesModelCapability[]required

One entry per capability the model implements. Each live model implements one today.

This view doesn’t include input slots. To see a model’s slot limits, read its offering in GET /v1/generation/capabilities.

Response

200

{
  "data": [
    {
      "id": "z-image-turbo",
      "capabilities": [
        {
          "capability": "image.generate",
          "description": "Z-Image Turbo. Fast, 8-step text to image.",
          "licence": "Apache-2.0",
          "available": true,
          "resolutions": ["1k", "2k"],
          "default_resolution": "1k",
          "qualities": [],
          "durations": [],
          "prices": [
            { "resolution": "1k", "duration_s": null, "credits": "0.08" },
            { "resolution": "2k", "duration_s": null, "credits": "0.30" }
          ],
          "licence_restricted": false,
          "licence_note": null
        }
      ]
    },
    {
      "id": "wan-2.2-i2v",
      "capabilities": [
        {
          "capability": "video.generate",
          "description": "Wan 2.2 image-to-video 14B. Start frame required. 480p, 5 s.",
          "licence": "Apache-2.0",
          "available": true,
          "resolutions": ["480p"],
          "default_resolution": "480p",
          "qualities": [],
          "durations": [5],
          "prices": [
            { "resolution": "480p", "duration_s": 5, "credits": "4.00" }
          ],
          "licence_restricted": false,
          "licence_note": null
        }
      ]
    }
  ]
}

See Models for what each model is good at.