{"slug": "ai-gateway-now-supports-asynchronous-video-generation", "title": "AI Gateway now supports asynchronous video generation", "summary": "Vercel's AI Gateway now supports asynchronous video generation, allowing applications to receive webhooks, poll for completion, or start a generation and retrieve results later, avoiding request timeouts. The update introduces `startVideo` and `getVideoStatus` functions, with all options supporting text-to-video, image-to-video, and reference-to-video inputs. Existing `generateVideo` calls continue to work as before.", "body_md": "[Video generation](https://vercel.com/docs/ai-gateway/modalities/video-generation) on AI Gateway can now run asynchronously.\n\nBy default, `generateVideo`\n\nkeeps one HTTP request to AI Gateway open until the result is ready. Because video generation can take seconds or minutes, that request can exceed request timeouts.\n\nWith asynchronous generation, your application can receive a webhook, poll for completion, or start a generation and retrieve the result in a later request.\n\nChoose an option based on whether your process can keep running and whether your application can receive webhooks:\n\nExisting `generateVideo`\n\ncalls continue to work as before. All four options support text-to-video, image-to-video, reference-to-video, and other video inputs.\n\nInstall the latest versions of the AI SDK and AI Gateway provider:\n\n`generateVideo`\n\nPass `webhook`\n\nto `generateVideo`\n\nto wait for a completion event without polling. AI Gateway sends an event when the job completes or fails. The SDK waits for that event, fetches the generated videos, and resolves the original `generateVideo`\n\ncall.\n\nThe calling process and webhook handler need a shared token and store so the delivery can be matched to the correct generation. `generateVideo`\n\ndoes not expose the signing secret for this workflow. See the [webhook verification documentation](https://vercel.com/docs/ai-gateway/modalities/video-generation#verifying-the-delivery) for the complete receiver pattern.\n\nBoth the polling and webhook options for `generateVideo`\n\nreturn `result.videos`\n\nas `GeneratedFile`\n\nobjects. The SDK downloads provider-hosted videos, making `uint8Array`\n\n, `base64`\n\n, and `mediaType`\n\navailable in either workflow.\n\n`generateVideo`\n\nAdd `poll`\n\nto an existing `generateVideo`\n\ncall:\n\nAI Gateway starts an asynchronous job, and the SDK sends a short status request at each interval until the job finishes. The calling process must remain running until `generateVideo`\n\nresolves, but no individual request to AI Gateway stays open for the full generation.\n\n`startVideo`\n\nreturns an operation as soon as AI Gateway accepts the job, without waiting for rendering to finish. Store that operation and pass it to `getVideoStatus`\n\nlater from the same process or another one:\n\nThe operation is JSON-serializable, so it can be stored in a database or passed through a queue. Your application controls how long to keep checking the job because this workflow has no built-in timeout.\n\nYou can also pass `webhookUrl`\n\nto `startVideo`\n\nto receive a completion event instead of checking the status. The start response includes the signing secret needed to verify the webhook.\n\nUnlike `generateVideo`\n\n, `getVideoStatus`\n\ndoes not download hosted videos. It returns provider URLs or inline bytes. Hosted URLs can expire, so download any videos you need to keep.\n\nEvery asynchronous generation appears on the [AI Gateway Logs page](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai-gateway%2Flogs&title=AI+Gateway+Logs) as soon as it starts. Jobs show as Running while generation is in progress and update when they complete or fail.\n\nUnder **Request Mode**, select **Async** to show only asynchronous jobs. Opening an entry shows the job ID and the request details.\n\nOnly asynchronous workflows create jobs. A standard `generateVideo`\n\ncall appears as a single completed request after the video is ready.\n\nFor size limits, idempotency for retried job starts, webhook delivery retries, and other operational details, read the [asynchronous video generation documentation](https://vercel.com/docs/ai-gateway/modalities/video-generation#asynchronous-generation) or [browse all video models](https://vercel.com/ai-gateway/models?type=video).", "url": "https://wpnews.pro/news/ai-gateway-now-supports-asynchronous-video-generation", "canonical_source": "https://vercel.com/changelog/ai-gateway-now-supports-asynchronous-video-generation", "published_at": "2026-08-25 00:00:00+00:00", "updated_at": "2026-08-25 17:17:00.887228+00:00", "lang": "en", "topics": ["ai-infrastructure", "developer-tools", "generative-ai"], "entities": ["Vercel", "AI Gateway", "AI SDK"], "alternates": {"html": "https://wpnews.pro/news/ai-gateway-now-supports-asynchronous-video-generation", "markdown": "https://wpnews.pro/news/ai-gateway-now-supports-asynchronous-video-generation.md", "text": "https://wpnews.pro/news/ai-gateway-now-supports-asynchronous-video-generation.txt", "jsonld": "https://wpnews.pro/news/ai-gateway-now-supports-asynchronous-video-generation.jsonld"}}