Tasks and inputs
TBC mischief 1 is listed for Image-text-to-video, Image-to-video. It accepts text, image and produces video. Use the publisher’s input format and preprocessing for your chosen deployment.
TBC mischief 1 is an image-to-video model built on Wan 2.2, sold on fal and OpenRouter at about half a cent per second for 3-5 s clips at up to 720p.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Pricing conditions: Indicative: about $0.005 per second of generated video on fal and OpenRouter (a 5 s clip is about $0.025). Confirm current pricing on your own account.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Half a cent per second of video. At that rate a five-second clip costs 2.5 cents and a hundred clips cost $2.50. That is the whole pitch for TBC mischief 1, the first commercial model from The Biological Computing Co., launched on 30 October 2026.
Underneath, it is image-to-video built on the open-weight Wan 2.2. What TBC adds is proprietary software it says was derived from measuring how living neurons, grown in its own lab, process information. The neurons stay in the lab. The findings become code, which adds under 0.1% to the parameter count and runs on ordinary accelerators.
The claimed payoff is roughly 5x faster generation than Wan 2.2 at matching quality. That is the company's statement, and both halves of it, speed and parity, are what you should measure.
| Field | Detail |
|---|---|
| Model IDs | tbc/mischief-1 (OpenRouter), TBC/mischief-1/image-to-video (fal) |
| Task | Image-to-video, optional text prompt |
| Resolution | 480p (854x480) or 720p (1280x720) |
| Aspect ratio | 16:9 only |
| Clip length | 3 or 5 seconds |
| Conditioning | First-frame image, optional reference images |
| Indicative price | ~$0.005 per second of output |
| Weights | Not published |
A prompt becomes optional once you pass a first frame. OpenRouter also accepts a seed (determinism is not guaranteed) and a callback URL so you can skip polling. It routes the model through one upstream provider and does not offer EU in-region routing, which matters if your data-residency rules are strict.
TBC's own launch material gives no resolution or duration limits at all. The figures above come from the marketplace listing, so if you need anything other than 16:9 landscape, test it before you plan around it.
Short, cheap, landscape clips from a still. Think product turntables, storyboard animatics, social previews by the thousand. It is not a long-form tool and not a vertical-video tool. For longer or higher-fidelity output, compare it against Seedance 2.5 or Veo 3.1 Fast, or browse the wider image-to-video list.
TBC says it is already applying the same process to newer open video bases, with early results showing larger efficiency gains. Expect a successor, and keep the model ID in configuration rather than in code.
Compare the model on the work you need to complete.
TBC mischief 1 is listed for Image-text-to-video, Image-to-video. It accepts text, image and produces video. Use the publisher’s input format and preprocessing for your chosen deployment.
Choose duration, resolution and frame rate together. Compare the cost of an accepted clip, including repeat generations.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
NVIDIA
Cosmos3-H-Dreams is NVIDIA's open real-time surgical world model: it streams Versius robot video from one endoscope frame and two-arm commands.
NVIDIA
Cosmos3-H-Embodied-Nano is NVIDIA's open 16B surgical world model that does forward dynamics, inverse dynamics and policy from one checkpoint.
NVIDIA
Cosmos3-Nano-Sim-Bimanual is NVIDIA's open 16B world model that simulates video of a two-armed AgiBot robot as it moves its camera and manipulates.
noiz-ai
Helix World (preview) is an open real-time world model from Noiz AI and HKUST that streams explorable 768x512 video with stereo sound that follows the camera.
Alibaba
Wan-Animate-2 is Alibaba Wan's open 14B character-animation model that drives a character from video directly, with text-controlled camera angle.
Z.ai / Zhipu AI
SCAIL-2 is Zhipu's open character-animation model that drives a reference character from any video, with no pose skeletons or masks. MIT licence.