Skip to main content

Inference API

Run AI inference on WiLine Edge Cloud — an OpenAI-compatible API with a catalog of hosted models. Create a key, call any model, and explore the catalog.

WiLine Edge Cloud Inference — an OpenAI-compatible API to run large language models, generate embeddings, transcribe audio, and synthesize speech.

Experiment with WiLine Edge Cloud models in the browser — chat with any model, tune parameters, and transcribe audio with Whisper. No code required.

Browse the WiLine Edge Cloud model catalog — filter and search models, compare capabilities and per-token pricing, and grab a model's id for your requests.

Create, find, and manage the API keys that authenticate your WiLine Edge Cloud inference requests — scope keys to models, track usage, and revoke them.

Copy-paste WiLine Edge Cloud inference requests for every use case — chat, streaming, tool calling, audio transcription, and listing models. Pick a language and model and the snippet updates.

API Reference