Inference at the edge

Edge AI

Edge AI hosts Zipper’s inference catalog. Call language, embedding, and classification models from Edge Functions without standing up a GPU fleet. Tokens are billed per workspace, and prompts can be redacted before they hit logs.

• ▸ Language models
• ▸ Embeddings
• ▸ Prompt redaction
• ▸ Per-workspace quotas

Auto-provisioned on every new zone. Read the Edge AI docs, including use cases and API examples. Manage it from the dashboard after you create an account.