Getting started

Base URL

All chat/translate traffic goes to the OpenAI-compatible gateway:

https://ai.ollalink.com/v1

Authentication

Send your partner key as a Bearer token on every request. Keep it server-side; never ship it to a browser.

Authorization: Bearer sk-partner-XXXXXXXXXXXXXXXXXXXXXXXX

A missing or invalid key returns HTTP 401.

Your first request

curl https://ai.ollalink.com/v1/chat/completions \
  -H "Authorization: Bearer sk-partner-XXXXXXXXXXXX" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "chat",
    "messages": [
      {"role":"system","content":"You are a helpful networking assistant."},
      {"role":"user","content":"In one sentence, what does BGP do?"}
    ],
    "max_tokens": 200
  }'

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(base_url="https://ai.ollalink.com/v1",
                api_key="sk-partner-XXXXXXXXXXXX")

resp = client.chat.completions.create(
    model="chat",
    messages=[{"role": "user", "content": "Explain OSPF in two sentences."}],
    max_tokens=300,
)
print(resp.choices[0].message.content)

Models at a glance

Model	Use it for
chat	General chat, RAG, summarization, vision (image input), tool/function calling
code	Dedicated coding (reasons first — send a large max_tokens, ≥ 4000)
local	Sovereign CPU chat (LFM2-2.6B) — prompts/outputs never leave our box; text-only, keep max_tokens modest
translate	Technical translation — keeps IPs, acronyms, and CLI in Latin

Call GET /v1/models for the live list. Full details in the API reference.

Health check

curl https://ai.ollalink.com/healthz    # -> ok