Quickstart
Create a NeuroAPI key, confirm it works, send your first prompt, and stream the response.
These four steps take you from signup to a streaming answer in about five minutes, using plain HTTP with no SDK. Skip any step you've already done: if you have a key, jump straight to asking your first question.
1. Get an API key
Sign in to the dashboard and open API Keys.
Click Create key, give it a label, and copy the secret.
The full secret is shown once, at creation time. Store it in a secret manager or environment variable before you close the dialog.
Make sure your account has an active plan under Billing & Plans - every API call requires it.
API keys look like neuro_<random>. The leading neuro_<8 chars> is
the public prefix, and wherever NeuroAPI surfaces a key (logs,
dashboards), it shows the prefix only.
2. Confirm your key works
GET /api/v1/health is the lightest authenticated call: it's free and
confirms your key and your active plan in one request.
curl -s https://api.neurobro.ai/api/v1/health \
-H "X-API-Key: $NEUROAPI_KEY" | jqExpected response:
{
"status": "healthy",
"service": "neuroapi",
"version": "0.1.19",
"authenticated": true,
"key_prefix": "neuro_a1b2c3d4",
"timestamp": "2026-05-08T12:34:56.789Z"
}version is the current build (the same value as the X-Build header
on every response), so yours may be newer than the example above.
3. Ask your first question
/agent/ask is the endpoint you'll build on. Send a prompt, pick a
mode (fast, smart, or max), and get a structured JSON answer
back with token usage and a request_id.
curl -s https://api.neurobro.ai/api/v1/agent/ask \
-H "Content-Type: application/json" \
-H "X-API-Key: $NEUROAPI_KEY" \
-d '{
"prompt": "Summarize the latest macroeconomic outlook for the eurozone.",
"mode": "smart"
}' | jqconst res = await fetch("https://api.neurobro.ai/api/v1/agent/ask", {
method: "POST",
headers: {
"Content-Type": "application/json",
"X-API-Key": process.env.NEUROAPI_KEY!,
},
body: JSON.stringify({
prompt: "Summarize the latest macroeconomic outlook for the eurozone.",
mode: "smart",
}),
})
const { answer, request_id, usage } = await res.json()import os, httpx
res = httpx.post(
"https://api.neurobro.ai/api/v1/agent/ask",
headers={"X-API-Key": os.environ["NEUROAPI_KEY"]},
json={
"prompt": "Summarize the latest macroeconomic outlook for the eurozone.",
"mode": "smart",
},
timeout=300,
)
data = res.json()Sample response:
{
"answer": "The European Central Bank held rates steady ...",
"mode": "smart",
"request_id": "8b3a2f0e-1d7e-4c6b-9b2a-f5e23a1c9d44",
"usage": {
"prompt_tokens": 124,
"completion_tokens": 256,
"cost_units": 2
}
}The X-Request-Id response header mirrors request_id - paste it when
reporting issues.
4. Stream the answer live
Set "stream": true to receive the answer token by token over
server-sent events (SSE) as it's generated, which suits chat UIs and long
responses. The stream closes with a final data: [DONE]\n\n. If the run
fails, the last event is {"type":"error", ...} with no [DONE] after
it, and the call isn't billed.
curl -N https://api.neurobro.ai/api/v1/agent/ask \
-H "Content-Type: application/json" \
-H "X-API-Key: $NEUROAPI_KEY" \
-d '{"prompt": "Walk me through the bull and bear case for NVDA right now.", "stream": true}'