runblob · API
runblob connects several video models through one pay-per-use API. This page gathers the models that generate video from a prompt or from an image: pick one by the inputs and duration you need, then open its page with live rates and a playground.
Text-to-video builds a clip from a written scene description — useful when you have no footage yet. Image-to-video animates an existing image or builds a scene around references while preserving the original composition. Some models accept text only, others accept images and references; the list below states which inputs each one takes.
Video is usually billed per second of output, so the total depends on version, resolution and duration, and models with a video reference may include extra input seconds in the estimate. No prices are quoted here: live USD rates load from the catalog on each model page and in the playground, and the calculator shows the estimated cost before you start.
Open the model you need and build the request in its playground: it generates a cURL with the exact endpoint, request fields and Bearer authorization. Move the request into server code so the secret key never reaches the browser, and pass images and video references as service-accessible URLs. Authentication, generation status and webhooks are described in full in the API documentation.
Billing is pay-per-use: you top up your runblob balance and spend it on API generations. Top-ups are charged in USD and processed by the payment provider, so budgeting matches the per-second rates shown on each model page.
Kuaishou
Inputs: Prompt or a starting image
The official Video 3.0 range supports clips up to 15 seconds; runblob offers several Kling generations.
ByteDance
Inputs: Prompt and multimodal references
The official Seedance 2.5 announcement introduces clips up to 30 seconds and multi-reference generation.
Google DeepMind
Inputs: Prompt (16:9 and 9:16 formats)
Google DeepMind describes Veo 3 with native audio generation; runblob offers Fast and Quality modes with text input.
Kuaishou
Inputs: References or first and last frame
A separate Frames version builds a transition between prepared start and end frames.
Kuaishou
Inputs: Prompt and multiple references
The catalog offers Standard (720p) and Pro (1080p); the range is officially named Video 3.0 Omni.
Text-to-video builds a scene from a written description; image-to-video starts from an existing image or references and preserves the original composition. Veo 3 in runblob works with text; Kling Video, Seedance, Kling O1 and O3 accept images and references.
Prices are not quoted in the text. Open the model page you need: live USD rates load from the catalog, and the playground calculator shows the estimated cost for the chosen version, resolution and duration before you start.
Yes. Choose a model that supports image input — for example Kling Video or Seedance — add an image URL and describe the movement. The URL must be reachable by the service; local file paths are not accepted.
Yes. runblob provides one integration and a shared balance: a single key and one Bearer authorization format are used for all the models listed here; only the version and request fields differ.