AI API reference

Endpoints, authentication and examples.

Base URL: https://api.timbler.org/v1 — below written as $BASE.

Authentication

Send your key as a bearer token:

Authorization: Bearer $TIMBLER_API_KEY

Endpoints

MethodPathDescription
GET/v1/modelsModels available to your key
POST/v1/chat/completionsOpenAI-compatible chat completions, including streaming (SSE)
POST/v1/messagesNative Anthropic Messages API for Anthropic models

Unsupported parameters are rejected explicitly with an OpenAI-style error rather than ignored.

Examples

curl $BASE/v1/chat/completions \
  -H "Authorization: Bearer $TIMBLER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "<model id from /v1/models>", "messages": [{"role": "user", "content": "Hello"}]}'

OpenAI SDK (Python):

from openai import OpenAI

client = OpenAI(base_url="$BASE/v1", api_key="$TIMBLER_API_KEY")
reply = client.chat.completions.create(
    model="<model id>",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)

Anthropic SDK (Python) — note the base URL has no /v1:

import anthropic

client = anthropic.Anthropic(base_url="$BASE", api_key="$TIMBLER_API_KEY")

Privacy

Requests are passed to the model provider and are not logged or stored by Timbler. We record usage facts only: key, model, token counts and time.

Last updated November 21, 2026