Skip to content

Quickstart

This guide takes you from zero to your first model response. It should take about five minutes.

1. Get an API key

Sign in to your Blaick account, then create an API key from the dashboard — or with the API itself once you have a session token (see Authentication).

An API key looks like this:

blk_a1b2c3d4e5f6g7h8i9j0

Save it now

The full key is shown only once, at creation time. Store it somewhere safe (a secret manager, not your source code). If you lose it, revoke it and create a new one.

Set it as an environment variable so the examples below work as-is:

export BLAICK_API_KEY="blk_a1b2c3d4e5f6g7h8i9j0"

2. List the models you can use

Every model has an id (a UUID) that you pass to the chat endpoint. Fetch the catalog:

curl https://api.blaick.ai/api/v1/models \
  -H "Authorization: Bearer $BLAICK_API_KEY"

Pick a model id from the response. See Models for how to choose.

3. Send your first message

curl https://api.blaick.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $BLAICK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "PASTE_A_MODEL_ID",
    "messages": [
      {"role": "user", "content": "Say hello in one sentence."}
    ]
  }'

import os
import requests

BASE = "https://api.blaick.ai/api/v1"
headers = {"Authorization": f"Bearer {os.environ['BLAICK_API_KEY']}"}

resp = requests.post(
    f"{BASE}/chat/completions",
    headers=headers,
    json={
        "model_id": "PASTE_A_MODEL_ID",
        "messages": [
            {"role": "user", "content": "Say hello in one sentence."}
        ],
    },
)
resp.raise_for_status()
data = resp.json()
print(data["content"])
print("Cost:", data["usage"]["cost_tokens"], "tokens")

const BASE = "https://api.blaick.ai/api/v1";

const resp = await fetch(`${BASE}/chat/completions`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.BLAICK_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model_id: "PASTE_A_MODEL_ID",
    messages: [{ role: "user", content: "Say hello in one sentence." }],
  }),
});

const data = await resp.json();
console.log(data.content);
console.log("Cost:", data.usage.cost_tokens, "tokens");

A successful response looks like:

{
  "id": "c0ffee00-0000-4000-8000-000000000000",
  "conversation_id": "11111111-2222-4333-8444-555555555555",
  "model_id": "claude-sonnet-4-20250514",
  "content": "Hello — it's great to meet you!",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 9,
    "total_tokens": 21,
    "cost_tokens": 42
  },
  "created_at": "2026-08-04T10:00:00Z"
}

That's it — you've made your first request, and usage.cost_tokens tells you exactly what it cost.

4. Turn on streaming

For a chat-like experience, stream the response token by token by adding "stream": true. The response becomes a Server-Sent Events stream:

curl -N https://api.blaick.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $BLAICK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "PASTE_A_MODEL_ID",
    "messages": [{"role": "user", "content": "Write a haiku about the sea."}],
    "stream": true
  }'

You'll receive a series of data: events:

data: {"type": "delta", "content": "Salt"}
data: {"type": "delta", "content": " wind"}
data: {"type": "usage", "input_tokens": 14, "output_tokens": 17, "total_tokens": 31, "cost_tokens": 62}
data: {"type": "done", "auto_routed": false, "routing_reason": null, "routing_task_type": null}

See Streaming Responses for how to parse these properly.

Where to go next