Axon AI API

Axon is HLD's proprietary data-sovereign AI — a family of language and embedding models that run entirely on HLD-controlled infrastructure within your legal jurisdiction. No prompt, completion, or document ever leaves your designated data residency region.

What makes Axon different

Name	Type	Required	Description
Data sovereignty	guarantee	No	All inference, embeddings, and RAG retrieval run on HLD servers in your chosen region. Zero data egress to third-party AI providers.
Jurisdiction compliance	guarantee	No	AU, US, EU, UK, and SG regions. Meets Australian Privacy Act, GDPR, UK GDPR, and local data localisation requirements.
Full audit trail	guarantee	No	Every API call is logged with user ID, model, token counts, and knowledge base references. Exportable via the audit endpoint.
Private knowledge bases	feature	No	RAG pipelines backed by your own documents — policies, runbooks, codebases — never mixed with other tenants.
OpenAI-compatible shape	feature	No	Completions and embeddings follow the same request/response structure as OpenAI. Drop-in for existing integrations.

Available models

Name	Type	Required	Description
axon-sovereign-1	model	No	Flagship 128k context model. Text, reasoning, code, structured output.
axon-sovereign-1-mini	model	No	Lightweight 32k model for classification, extraction, high-throughput tasks.
axon-embed-1	model	No	1536-dim embedding model for semantic search and RAG pipelines.

Data residency regions

Name	Type	Required	Description
au	region	No	Australia — Sydney
us	region	No	United States — Virginia
eu	region	No	European Union — Frankfurt
uk	region	No	United Kingdom — London
sg	region	No	Singapore

Base URL

bash

https://api.hldgroup.org/v1/axon

Authentication

bash

curl -X POST https://api.hldgroup.org/v1/axon/completions \
  -H "x-internal-secret: <your-api-key>" \
  -H "x-user-id: usr_01hxyz" \
  -H "x-tenant-id: ten_01hxyz" \
  -H "x-platform-role: tenant-standard-user" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "axon-sovereign-1",
    "data_residency": "au",
    "messages": [
      { "role": "user", "content": "Summarise our security incident policy." }
    ]
  }'

Note:All read operations (completions, embeddings, RAG queries) are available to tenant-standard-user and above. Write operations (create/delete knowledge bases, upload documents) require tenant-system-admin.

Quick start: RAG over your own documents

bash

# 1. Create a knowledge base in your region
curl -X POST https://api.hldgroup.org/v1/axon/knowledge-bases \
  -H "x-internal-secret: <key>" -H "x-tenant-id: ten_01hxyz" \
  -H "x-user-id: usr_01hxyz" -H "x-platform-role: tenant-system-admin" \
  -H "Content-Type: application/json" \
  -d '{ "name": "Security runbooks", "data_residency": "au" }'

# 2. Upload a document
curl -X POST https://api.hldgroup.org/v1/axon/knowledge-bases/kb_01hxyz/documents \
  -H "x-internal-secret: <key>" -H "x-tenant-id: ten_01hxyz" \
  -H "x-user-id: usr_01hxyz" -H "x-platform-role: tenant-system-admin" \
  -H "Content-Type: application/json" \
  -d '{ "filename": "ransomware-response.md", "mime_type": "text/markdown", "content": "# Ransomware Response\n..." }'

# 3. Query it
curl -X POST https://api.hldgroup.org/v1/axon/knowledge-bases/kb_01hxyz/query \
  -H "x-internal-secret: <key>" -H "x-tenant-id: ten_01hxyz" \
  -H "x-user-id: usr_01hxyz" -H "x-platform-role: tenant-standard-user" \
  -H "Content-Type: application/json" \
  -d '{ "query": "What are the first steps when ransomware is detected?" }'

Models Completions