OpenRouter launches video generation API, an interface that calls mainstream models such as Sora 2, Veo 3.1, Seedance, and others.

ME News Report, April 16 (UTC+8), according to Dongcha Beating monitoring, the AI model aggregation platform OpenRouter officially launched a video generation API, supporting text-to-video and image-to-video in the initial release, integrated with Seedance 2.0/1.5, Veo 3.1, Wan 2.7/2.6, and Sora 2 Pro, with further expansion planned. The API fragmentation in the video generation field is much more severe than that of text models: request formats vary across providers, parameter naming differs, billing units are inconsistent, and even different capabilities within the same model family (text-to-video, image-to-video, reference character generation) often correspond to different endpoints. OpenRouter’s approach is to build a unified schema on top, automatically routing requests to the correct endpoint based on request parameters. Including an image routes to image-to-video, specifying a reference character routes to the character consistency endpoint, so developers don’t need to worry about underlying differences. Parameter normalization also covers easily overlooked details. For example, Veo 3.1 supports 4, 6, 8-second clips, Wan 2.6 supports 5 or 10 seconds, and incorrect durations will directly result in an error. OpenRouter provides a model capability query endpoint /api/v1/videos/models, which returns each model’s supported resolution, duration, aspect ratio, pricing, and model-specific parameters, allowing developers or proxy programs to check before testing to avoid trial-and-error. Since video generation takes minutes, the API operates asynchronously: after submitting prompts, it returns a task ID, and the video can be retrieved once completed. OpenRouter also open-sourced a multimodal workflow demonstration app, showcasing the chaining process of generating detailed prompts with LLM, creating characters with image models, and generating scenes with video models. This is the most direct benefit of the unified routing for video generation: developers can combine text, image, and video models under a single API without separately integrating each provider’s SDK. (Source: BlockBeats)