List Available AI Models (Legacy API)

GET

models

cURL

curl "https://api.hedra.com/web-app/public/models" \
  -H "X-API-Key: $HEDRA_API_KEY"

[
  {
    "slug": "<string>",
    "name": "<string>",
    "description": "<string>",
    "type": "<string>",
    "price_details": {
      "credit_cost": 123,
      "unit_scale": 123,
      "billing_unit": "<string>"
    },
    "id": "<string>",
    "aspect_ratios": [
      "<string>"
    ],
    "aspect_ratio_range": {
      "[0]": 123,
      "[1]": 123
    },
    "resolutions": [
      "<string>"
    ],
    "default_resolution": "<string>",
    "durations": [
      "<string>"
    ],
    "target_frame_rates": [
      123
    ],
    "fps_engines": [
      {
        "name": "<string>",
        "price_multiplier": 123
      }
    ],
    "requires_character_orientation": true,
    "eta_ms": 123,
    "tags": [
      "<string>"
    ],
    "max_duration_ms": 123,
    "custom_resolution": true,
    "pricing": {
      "base_cost": 123,
      "credits_per_second": 123,
      "modifiers": {}
    },
    "credit_range": {
      "[0]": 123,
      "[1]": 123
    },
    "dimensions": {},
    "min_prompt_length": 123,
    "max_prompt_length": 123,
    "supports_prompt_enhancement": true,
    "prompt_enhancement_mode": "generic",
    "inputs": [
      {
        "mode": "<string>",
        "slots": [
          {
            "type": "<string>",
            "role": "<string>",
            "required": false,
            "min_count": 1,
            "max_count": 1,
            "max_file_size_bytes": 123,
            "min_dimension_px": 123,
            "max_dimension_px": 123,
            "min_duration_ms": 123,
            "max_duration_ms": 123,
            "max_total_duration_ms": 123,
            "min_aspect_ratio": 123,
            "max_aspect_ratio": 123
          }
        ],
        "aspect_ratios": [
          "<string>"
        ],
        "resolutions": [
          "<string>"
        ],
        "default_resolution": "<string>",
        "custom_resolution": true,
        "dimensions": {}
      }
    ],
    "conditional_constraints": [
      {
        "when": "<unknown>",
        "then": "<unknown>"
      }
    ],
    "options": [
      {
        "name": "<string>",
        "type": "enum",
        "default": "<string>",
        "values": [
          "<string>"
        ]
      }
    ],
    "alternative_model_slugs": [
      "<string>"
    ],
    "logo_url": "<string>",
    "premium": true,
    "display_order": 123
  }
]

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

X-API-Key

string

header

required

Query Parameters

types

enum<string>[] | null

Generation type enum

NOTE: this enum is used to determine the type of generation and is used to determine the type of asset that will be generated.

Available options:

image,

video,

text_to_speech,

speech_to_speech,

voice_clone,

audio_isolation,

video_stitching,

video_upscale,

video_to_video,

video_background_removal,

image_upscale,

agent_response,

audio_from_video,

text_to_sound,

music,

assets_to_image_text_prompt,

assets_to_audio_text_prompt

Response

Successful Response

slug

string

required

Stable cross-environment identifier for the model, e.g. google/nano-banana. Unique and identical across local/staging/production. Prefer slug over id when referencing models — id is environment-specific and will be removed in a later migration (model-registry plan step 7).

name

string

required

Name of the model

description

string | null

required

Description of the model.

type

string

required

Type of generation the model applies to.

price_details

AIModelPrice · object

required

Pricing details of the model.

Show child attributes

string | null

Environment-specific UUID of the model, or null for a code-backed model with no ai_models row (identified by slug). Being removed in favor of slug (model-registry plan step 7); prefer slug.

aspect_ratios

string[] | null

Aspect ratios the model supports.

aspect_ratio_range

Aspect Ratio Range · object | null

If set to (min, max), the model accepts any keyframe whose width/height ratio is in [min, max], not just the values in aspect_ratios. The model snaps the output to its internal grid. aspect_ratios then serves as UI/preset labels rather than as an enum gate.

Show child attributes

resolutions

string[] | null

Resolutions the model supports.

default_resolution

string | null

Backend-declared default output resolution for this model.

durations

string[] | null

Durations the model supports.

target_frame_rates

integer[] | null

Output frame rates a video-upscale model can interpolate up to. Absent when the model offers no frame-rate control.

fps_engines

FpsEngineOption · object[] | null

Interpolation engines offered with target_fps, in display order; the first is the default. price_multiplier scales the whole upscale charge.

Show child attributes

requires_character_orientation

boolean | null

Whether the model requires character orientation (motion control).

eta_ms

integer | null

Average generation duration in milliseconds.

tags

string[] | null

Tags for model categorization.

max_duration_ms

integer | null

Maximum output duration in milliseconds for video/audio models.

custom_resolution

boolean | null

Whether the model supports custom resolution.

pricing

Pricing · object | null

Extensible pricing information with dimension modifiers for resolution, audio, etc.

Show child attributes

credit_range

Credit Range · object | null

Min and max credits one generation can cost across the model's resolution/duration grid, computed server-side through the model's own pricing (sentinel durations billed as charged, audio-off discounts included). Null for models priced from a resolved asset (audio-driven, extension) — render the base price_details cost instead.

Show child attributes

dimensions

Dimensions · object | null

Width and height for each aspect_ratio and resolution tuple.

Show child attributes

min_prompt_length

integer | null

Minimum character count for text prompts. Null means no minimum.

max_prompt_length

integer | null

Maximum character count for text prompts. Null means no maximum.

supports_prompt_enhancement

boolean

default:true

Whether the model accepts automatic server-side prompt enhancement during generation.

prompt_enhancement_mode

enum<string>

default:generic

Whether enhancement is unavailable, uses the generic contract, or uses a reviewed model-specific guide.

Available options:

unsupported,

generic,

model_specific

inputs

InputMode · object[] | null

List of input modes the model supports. Each mode groups mutually exclusive input slots. The frontend picks one mode. text_to_video (no inputs) is always implicitly available for VIDEO type models. Null means the model takes no media input.

Show child attributes

conditional_constraints

ConditionalConstraint · object[] | null

Machine-readable conditional input rules the backend enforces at submit. Each rule's when is conjunctive over the closed keys resolution (matched against the effective resolution: the requested one, or default_resolution when omitted) and references_present; its then narrows what the model advertises — audio_input_max_duration_ms caps the driving audio, durations (int ms) replaces the offered durations, and disallowed_resolutions removes resolutions. When several rules match: numeric caps take the minimum, durations intersect, disallowed_resolutions union. Null when the model declares none.

Show child attributes

options

ModelOption · object[] | null

Scalar options the model accepts per generation (closed enums and booleans), price-neutral unless a value declares a price_multiplier — the quote endpoint reflects any declared multiplier, so clients never do pricing math. Submit validates the request's options payload against this declaration; every default equals the provider's own default, so omission and explicit-default are equivalent. Null when the model publishes none.

Show child attributes

alternative_model_slugs

string[] | null

Ordered slugs of models to suggest when the user switches away after a failed generation (moderation/capacity rejection). Slug is the stable catalog identity to match on; the legacy id is nullable and absent on newer models, so it cannot address them. Only models present and not disabled in this build are listed. Null when the model declares no alternatives.

logo_url

string | null

URL of the model's logo in SVG format.

premium

boolean

default:true

Whether this is a premium model.

display_order

integer | null

Display order for UI sorting. Lower values appear first.

⌘I

cURL

curl "https://api.hedra.com/web-app/public/models" \
  -H "X-API-Key: $HEDRA_API_KEY"

[
  {
    "slug": "<string>",
    "name": "<string>",
    "description": "<string>",
    "type": "<string>",
    "price_details": {
      "credit_cost": 123,
      "unit_scale": 123,
      "billing_unit": "<string>"
    },
    "id": "<string>",
    "aspect_ratios": [
      "<string>"
    ],
    "aspect_ratio_range": {
      "[0]": 123,
      "[1]": 123
    },
    "resolutions": [
      "<string>"
    ],
    "default_resolution": "<string>",
    "durations": [
      "<string>"
    ],
    "target_frame_rates": [
      123
    ],
    "fps_engines": [
      {
        "name": "<string>",
        "price_multiplier": 123
      }
    ],
    "requires_character_orientation": true,
    "eta_ms": 123,
    "tags": [
      "<string>"
    ],
    "max_duration_ms": 123,
    "custom_resolution": true,
    "pricing": {
      "base_cost": 123,
      "credits_per_second": 123,
      "modifiers": {}
    },
    "credit_range": {
      "[0]": 123,
      "[1]": 123
    },
    "dimensions": {},
    "min_prompt_length": 123,
    "max_prompt_length": 123,
    "supports_prompt_enhancement": true,
    "prompt_enhancement_mode": "generic",
    "inputs": [
      {
        "mode": "<string>",
        "slots": [
          {
            "type": "<string>",
            "role": "<string>",
            "required": false,
            "min_count": 1,
            "max_count": 1,
            "max_file_size_bytes": 123,
            "min_dimension_px": 123,
            "max_dimension_px": 123,
            "min_duration_ms": 123,
            "max_duration_ms": 123,
            "max_total_duration_ms": 123,
            "min_aspect_ratio": 123,
            "max_aspect_ratio": 123
          }
        ],
        "aspect_ratios": [
          "<string>"
        ],
        "resolutions": [
          "<string>"
        ],
        "default_resolution": "<string>",
        "custom_resolution": true,
        "dimensions": {}
      }
    ],
    "conditional_constraints": [
      {
        "when": "<unknown>",
        "then": "<unknown>"
      }
    ],
    "options": [
      {
        "name": "<string>",
        "type": "enum",
        "default": "<string>",
        "values": [
          "<string>"
        ]
      }
    ],
    "alternative_model_slugs": [
      "<string>"
    ],
    "logo_url": "<string>",
    "premium": true,
    "display_order": 123
  }
]

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Getting Started

Guides

API Reference

List Available AI Models (Legacy API)

Authorizations

Query Parameters

Response