Skip to content
Navon Docs

Token Factory

Layer 05 · Compute & Inference — Net-new this year

Serve every open-weight and custom model behind one governed, OpenAI-compatible API, metered by the token and running on Navon metal, so no prompt or output ever leaves the country.

Capabilities

Section titled “Capabilities”
  • One OpenAI-compatible API for chat, embeddings, and rerank
  • Open-weight model catalog, including African-language models hosted nowhere else
  • Serverless shared endpoints and dedicated endpoints with an SLA
  • Batch inference at roughly half the price of live requests
  • Fine-tuning, LoRA, and distillation, deployed in one step
  • Retrieval that resolves through the Data Lake ontology
  • Per-token billing, zero retention by default, usage fully observable

API

Section titled “API”

This product exposes an API. The reference is generated from its OpenAPI spec (openapi/token-factory.yaml).