Media

Media is one catalogue, one library and five routes, shared by the REST API and an agent’s tools:

	Route	Answers
Images	`POST /v1/media/images`	Synchronous — the finished files, in one call.
Stock photos	`GET /v1/media/stock`	Licensed photos by description; import one as a file with `POST /v1/files/imports`.
Video	`POST /v1/media/videos`	A `202` media job you read back with `GET /v1/media/{id}` and list with `GET /v1/media`.
Clips	`POST /v1/media/clips`	A `202` clip job — scored, captioned short clips cut from a long video.
Audio	`POST /v1/media/audio/transcriptions` · `POST /v1/media/audio/speech` · `POST /v1/media/audio/conversations`	Transcription as a media job; speech and a spoken reply as finished files.
Models	`GET /v1/media/models`	The catalogue below — which `model` each route accepts.
Library	`GET /v1/files`	Every result lands in Files with its `source` — filter by `kind`, `source`, `tag` or `search`.

There is no fixed list of generation models. The catalogue is read from the provider on every call, so a model published today is callable today. Search it here; pass what you find as model to POST /v1/media/images / POST /v1/media/videos or to generate_image / generate_video, or pin it on an agent with tools.configs.<tool>.config.models.

The media model object

string

Always media_model.

string

The model’s id. This is what model takes, on the generation routes and on the tools.

string

The model’s display name.

string

image · video · stt · tts · s2s. The three audio kinds are the audio catalogues.

string

What the model is good at, in the model author’s own words.

No price is published here, for the same reason GET /v1/models publishes none: a generation job is billed what it actually cost, and that is only knowable once the job has finished. See Pricing.

Search models

GET /v1/media/models — scope agents:read

string

required

image · video · stt · tts · s2s. Required: each is its own capability with its own catalogue — the audio ones are described on Audio.

string

Matches a model’s id, name or description. Omit it to list them all.

number

Page size, 1–100.

string

The next_cursor of the previous page. Opaque — it is not a row id.

curl -fsSL "https://api.vetta.sh/v1/media/models?kind=video&search=seedance" \
  -H "authorization: Bearer sk_live_..."

{
  "object": "list",
  "data": [
    {
      "object": "media_model",
      "id": "bytedance/seedance-2.5",
      "name": "Seedance 2.5",
      "kind": "video",
      "description": "A text- and image-to-video model for short cinematic clips.",
    }
  ],
  "has_more": false,
  "next_cursor": null
}

Ordering is cheapest-first where the provider publishes a per-output price, which today is the image catalogue only. That is why an image request can leave model out and a video request must name one. A deploy with no generation provider configured answers 501 feature_not_configured rather than an empty list — “nothing is configured here” and “the provider has no models” are different facts.

Introduction

Core resources

Platform

Identity

The media model object

Search models

​The media model object

​Search models

The media model object

Search models