Create an API key and use gemma3, llava and qwen2.5 from your own apps.
Save it now. For security it can't be shown again.
Example:
Save it now. It can't be shown again.
Copy it now. It can't be shown again.
Send your key in a header on every request. Keys in URLs (?key=...) are deliberately not supported because URLs get logged.
Authorization: Bearer sk-ol-xxxxxxxx # or x-api-key: sk-ol-xxxxxxxx
| Method | URL | Auth | Purpose |
|---|---|---|---|
| GET | /health | none | Service status |
| POST | /v1/keys/signup | none | Create your own API key (if enabled) |
| GET | /v1/models | key | List models you can use |
| POST | /v1/chat/completions | key | OpenAI-compatible chat (streaming, vision) |
| POST | /v1/chat | key | Native chat (NDJSON streaming) |
| POST | /v1/generate | key | Single-prompt completion |
| POST | /v1/embeddings | key | Text embeddings |
| GET | /v1/usage | key | Tokens used and remaining this month |
| GET | /v1/keys/me | key | Your key's settings and expiry |
| POST | /v1/keys/rotate | key | Get a new secret; old one stops working |
| DELETE | /v1/keys/me | key | Revoke your key |
curl {{BASE}}/v1/chat/completions \
-H "Authorization: Bearer sk-ol-xxxxxxxx" \
-H "Content-Type: application/json" \
-d '{"model":"gemma3:4b","messages":[{"role":"user","content":"Hello!"}]}'
from openai import OpenAI
client = OpenAI(base_url="{{BASE}}/v1", api_key="sk-ol-xxxxxxxx")
r = client.chat.completions.create(
model="qwen2.5:7b",
messages=[{"role": "user", "content": "Explain APIs simply"}],
)
print(r.choices[0].message.content)
const r = await fetch("{{BASE}}/v1/chat/completions", {
method: "POST",
headers: { "Authorization": "Bearer sk-ol-xxxxxxxx", "Content-Type": "application/json" },
body: JSON.stringify({ model: "gemma3:4b", messages: [{ role: "user", content: "Hi" }] }),
});
console.log((await r.json()).choices[0].message.content);
{"model": "llava:latest", "messages": [{"role": "user", "content": [
{"type": "text", "text": "What is in this image?"},
{"type": "image_url", "image_url": {"url": "data:image/png;base64,iVBORw0..."}}
]}]}
Only base64 data: images are accepted. The server never downloads remote URLs.
401 invalid/expired/revoked key · 403 model or IP not allowed · 413 request too large · 422 invalid input · 429 rate limit or quota (see Retry-After) · 502/503 model backend unavailable or busy.