Quickstart
Get a token and send your first request.
Get a token
Ask an admin for a token. Admins create tokens in the dashboard under
Gebruikers, then your user, then Token. The token is shown once and
looks like ic_ followed by 43 characters. Export it in your shell:
export INDICIA_TOKEN="ic_..."If you use indicia code, you already have a personal token in
~/.indicia/config.json.
Send a request
Call /v1/chat/completions with curl or
the OpenAI SDK.
curl https://code.test.indicia-ai.com/v1/chat/completions \
-H "Authorization: Bearer $INDICIA_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "indicia/snel",
"messages": [{"role": "user", "content": "Say hello"}]
}'The response is a chat.completion object:
{
"id": "chatcmpl-72d16bc1-e432-4eba-9d46-c64d93bfe92b",
"object": "chat.completion",
"created": 1791897901,
"model": "indicia/snel",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello!"},
"finish_reason": "stop"
}
],
"usage": {"prompt_tokens": 8, "completion_tokens": 6, "total_tokens": 14}
}Use the Anthropic SDK
The same token works with the Anthropic SDK on
/v1/messages.
pip install anthropicimport os
from anthropic import Anthropic
client = Anthropic(
base_url="https://code.test.indicia-ai.com",
api_key=os.environ["INDICIA_TOKEN"],
)
message = client.messages.create(
model="claude-sonnet-5-5",
max_tokens=1024,
messages=[{"role": "user", "content": "Say hello"}],
)
print(message.content[-1].text)Base URLs differ per SDK
The OpenAI SDK takes the base URL with /v1. The Anthropic SDK adds /v1
itself, so give it the bare host.