> ## Documentation Index > Fetch the complete documentation index at: https://www.edenai.co/docs/llms.txt > Use this file to discover all available pages before exploring further. # Video Generation > Generate video with the OpenAI-compatible /v3/videos endpoints. export const TechArticleSchema = ({title, description, path, articleSection, about, proficiencyLevel = "Beginner", dependencies, keywords = [], datePublished, dateModified, image, inLanguage = "en"}) => { const baseUrl = "https://www.edenai.co/docs"; const canonicalUrl = `${baseUrl}/${path}`.replace(/\/+$/, ""); const ogParams = new URLSearchParams({ division: articleSection || "", title: title || "", description: description || "" }); const resolvedImage = image || `https://edenai.mintlify.app/_mintlify/api/og?${ogParams.toString()}`; const data = { "@context": "https://schema.org", "@type": "TechArticle", "@id": `${canonicalUrl}#techarticle`, mainEntityOfPage: { "@type": "WebPage", "@id": canonicalUrl }, headline: title, name: title, description: description, url: canonicalUrl, inLanguage: inLanguage, isPartOf: { "@type": "WebSite", name: "Eden AI Documentation", url: baseUrl }, author: [{ "@type": "Organization", name: "Eden AI", url: "https://www.edenai.co/" }], publisher: { "@type": "Organization", name: "Eden AI", url: "https://www.edenai.co/", logo: { "@type": "ImageObject", url: "https://www.edenai.co/assets/logo.png" } } }; if (articleSection) data.articleSection = articleSection; if (about) data.about = { "@type": "Thing", name: about }; if (proficiencyLevel) data.proficiencyLevel = proficiencyLevel; if (dependencies) data.dependencies = dependencies; if (keywords && keywords.length) data.keywords = keywords; if (datePublished) data.datePublished = datePublished; if (dateModified) data.dateModified = dateModified; data.image = Array.isArray(resolvedImage) ? resolvedImage : [resolvedImage]; const json = JSON.stringify(data); const schemaId = `techarticle-${canonicalUrl}`; React.useEffect(() => { if (typeof document === "undefined") return; document.querySelectorAll(`script[data-schema-id="${schemaId}"]`).forEach(n => n.remove()); const script = document.createElement("script"); script.type = "application/ld+json"; script.dataset.schemaId = schemaId; script.textContent = json; document.head.appendChild(script); return () => script.remove(); }, [json, schemaId]); return null; }; Generate videos through Eden AI's OpenAI-compatible video endpoints. Point any OpenAI client at `https://api.edenai.run/v3` and the video API works as a drop-in replacement for OpenAI's video generation. ## Overview The surface is a facade over `POST /v3/universal-ai/async` for `video/generation_async`: same providers, same pricing, same job table, same polling and webhooks. Only the wire shape is OpenAI's. | Method | Path | Purpose | | -------- | ------------------------------- | ------------------------------------------------------------- | | `POST` | `/v3/videos` | Start a job (JSON or multipart). Returns 200 + video object | | `GET` | `/v3/videos/{video_id}` | Job status as a video object | | `GET` | `/v3/videos/{video_id}/content` | The mp4: 302 to the file while its link is valid, bytes after | | `GET` | `/v3/videos` | Your video jobs, newest first (`limit` 1-100, `after` cursor) | | `DELETE` | `/v3/videos/{video_id}` | Delete a finished job (409 while it is still running) | | `GET` | `/v3/videos/models` | Models callable here, as `provider/model` ids | Video models are **not** in `GET /v3/models` (chat / responses only) nor in `GET /v3/images/models`. ## Usage ```python OpenAI SDK theme={null} from openai import OpenAI client = OpenAI(base_url="https://api.edenai.run/v3", api_key="YOUR_API_KEY") video = client.videos.create_and_poll( model="pruna/p-video", prompt="A red paper boat drifting on a calm pond at sunrise", seconds="5", size="1280x720", ) assert video.status == "completed" client.videos.download_content(video.id).write_to_file("boat.mp4") ``` ### Image-to-Video Image-to-video with the SDK's file upload (multipart): ```python OpenAI SDK (Multipart) theme={null} with open("keyframe.png", "rb") as f: video = client.videos.create( model="pruna/p-video", prompt="the boat sails away", input_reference=f ) ``` Image-to-video with JSON, referencing an upload or a URL: ```bash cURL (JSON) theme={null} curl -X POST "https://api.edenai.run/v3/videos" \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "pruna/p-video", "prompt": "the boat sails away", "input_reference": {"image_url": "https://example.com/keyframe.png"} }' ``` `input_reference` accepts `{"file_id": ""}` or `{"image_url": "https://..."}` (an http(s) URL to a JPEG or PNG). Base64 data URLs are rejected; upload the image instead. ## Request fields | OpenAI field | Maps to universal-ai | Notes | | ----------------- | -------------------- | -------------------------------------------------------------------------------- | | `model` | model string | Required. E.g., `provider/model`. Bare names (`sora-2`) are rejected with a 400. | | `prompt` | `text` | Required. Text describing the content to generate. | | `seconds` | `duration` | String or integer, any positive value; omitted uses the model's default. | | `size` | `dimension` | `WIDTHxHEIGHT`. Omitted uses the provider's default resolution. | | `input_reference` | `file` | Object or file part. See examples above. | Eden extensions (not in OpenAI's API): `seed`, `provider_params` (gated by the per-provider allow-list), `webhook_receiver`, `user_webhook_parameters`. On a JSON body, unknown fields are rejected (422), so `fallbacks` and `@edenai` routing are not available here. A multipart form silently ignores unknown form fields instead. ## Video object ```json theme={null} { "id": "e5eef4b4-acd1-4eb9-a5c9-2769271e42f5", "object": "video", "status": "queued", "progress": 0, "created_at": 1757435495, "completed_at": null, "expires_at": null, "model": "pruna/p-video", "seconds": "5", "size": "1280x720", "remixed_from_video_id": null, "error": null, "provider": "pruna", "cost": 0 } ``` * `status`: `queued` on the create response, `in_progress` on later reads while the job runs, then `completed` or `failed`. `progress` goes from 0 to 100. * `provider` and `cost` (USD) are Eden extensions. `cost` is 0 while the job is queued or in progress, and updates to the settled amount once the job completes or fails. * `id` is the universal-ai job id: the same job is visible at `GET /v3/universal-ai/async/{id}`. ## Limitations * **Response `size`:** `size` is only echoed on the create response; reads return `null` (the job row does not store the request). `seconds` on reads is the duration the provider actually rendered. * **Unsupported Routes:** No remix, extensions, edits or characters: these OpenAI routes answer 400. * **Keyset Pagination:** `after` is a keyset cursor on `(created_at, id)`: pass the previous page's `last_id` to get the jobs that follow it in newest-first order, rather than an offset-style page number. * Only the `video` content variant (no thumbnails / spritesheets). * The content redirect points at a signed link valid for 7 days; after that the endpoint serves the stored bytes directly. * Authentication errors (401 for a bad token, 403 when the header is missing), rate-limit (429) and query-parameter validation errors (e.g. `?limit=0`) use the platform's `{"detail": ...}` shape rather than the OpenAI error envelope. ## Pricing Identical to universal-ai video generation: `info_pricing` rows per provider/model, per-second or per-request, with resolution tiers where seeded. Nothing is priced differently for coming through this surface.