# `LlmCall.Media.Dialect.MiniMax.Video`
[🔗](https://github.com/gilbertwong96/llm_call/blob/main/lib/llm_call/media/dialect/minimax/video.ex#L1)

MiniMax Hailuo video generation (`v1`).

Three calls, expressed with the `Operation` state machine:

1. submit `POST /v1/video_generation` -> `task_id`;
2. poll `GET /v1/query/video_generation?task_id=…` -> `Preparing` /
   `Queueing` / `Processing` / `Success` / `Fail`;
3. on `Success` the query returns only a `file_id`, so the operation stays
   `:in_progress` and `next` is `GET /v1/files/retrieve?file_id=…`; that payload
   carries `file.download_url`, which completes the job.

MiniMax reports errors as HTTP 200 with a non-zero `base_resp.status_code`, so
a non-zero `base_resp` is a `:provider` error regardless of transport status.

`resolution`, `prompt_optimizer`, `fast_pretreatment`, `callback_url`, and
`extra` are reached through `provider_options.minimax`. The `v2` (H3) surface
is not implemented.

# `validate_request`

```elixir
@spec validate_request(LlmCall.Media.Request.t(), LlmCall.Config.t()) ::
  :ok | {:error, LlmCall.Error.t()}
```

Runs the shared media validation pipeline with the codec's own checks.

---

*Consult [api-reference.md](api-reference.md) for complete listing*
