Managed & in-region
Models run as a managed service in the AWS Regions you choose, so inference stays within your selected geography rather than crossing arbitrary boundaries.
CineCLI is powered by Cine Model — our own self-developed multimodal model purpose-built for short-drama generation, spanning script, storyboard, character consistency, visuals, voice and subtitles. It is augmented by leading third-party foundation models — OpenAI GPT, Google Gemini and Qwen — routed per task by intelligent routing. Every call runs under Cine Model Guardrails and our own governance controls.
CineCLI leads with our first-party Cine Model and selects the best model per task rather than relying on a single model for everything. The table below summarizes how each model is used today.
| Model | Provider | Used in CineCLI for | Notes |
|---|---|---|---|
| Cine Model (flagship, self-developed) | CineCLI (first-party) | End-to-end short-drama generation — script, storyboard, character consistency, scene visuals, voice and subtitles. | Our own multimodal model, purpose-built for short drama; drives the core pipeline and keeps characters consistent across shots. |
| OpenAI GPT | OpenAI | Script writing, story and scene development, reasoning, and content classification that supports moderation. | Selected per task for complex writing and reasoning; faster variants for classification and routing. |
| Google Gemini | Text and multimodal understanding — analyzing scripts and reference media, structuring scenes, and assisting moderation. | Used per task for rich multimodal understanding alongside Cine Model. | |
| Qwen | Alibaba | Additional language and multimodal tasks — drafting, classification, retrieval and continuity support. | Routed in where its strengths suit a task; subject to the same guardrails and provenance. |
The Cine Model platform lets CineCLI lead with our self-developed model and reach leading third-party models through one managed interface, while keeping data handling, security and content controls consistent across providers.
Models run as a managed service in the AWS Regions you choose, so inference stays within your selected geography rather than crossing arbitrary boundaries.
Data is encrypted in transit and at rest. Content sent to third-party foundation models is not used to train their underlying base models.
Configurable content filters apply policies for harmful content and denied topics, so the same safety rules can wrap every model regardless of provider.
Cine Model's evaluation tooling helps us compare models on quality and safety for a given task before promoting one into the pipeline.
For production workloads we can reserve dedicated capacity, giving predictable latency and throughput during peak production runs.
A single managed API spanning Cine Model, OpenAI GPT, Google Gemini, Qwen and others lets us choose the best model per task without bespoke integrations.
No model is called directly. Each request is wrapped in Cine Model Guardrails and our own policy checks, and every generated asset is screened again before it can be used. Media that models produce carries provenance signals so it can be recognized as AI-generated.
We treat model selection as a governed decision, with records of which model and version produced each result.
Talk to us about model selection, in-region deployment and how CineCLI governs every generation, or request access to try it.