What problem does it solve?
It removes the friction of calling CloudBase AI models from browser-based Web applications by providing a safe, correct way to select models, verify eligibility, and ensure the target model is enabled before generating text.
Core Features & Use Cases
- Browser-first AI calls for Web UIs: Supports calling AI models directly from the frontend (Vue/React/Next/Nuxt/SPAs/admin dashboards) without proposing a Node.js or proxy first.
- Streaming and non-streaming text generation: Use generateText for single responses or streamText for incremental token/chunk delivery.
- Production guardrails for model readiness: Enforces a two-step preflight (Token Credits resource pack eligibility, then DescribeAIModels + catalog lookup + UpdateAIModel when needed), so runtime “model not found/enabled” failures are minimized.
Quick Start
Use the ai-model-web skill to call the requested model from the page by streaming the generated text into your UI, after first confirming Token Credits eligibility and ensuring the exact model SKU is enabled in the cloudbase group.