Skip to content
CircuitNotionDeveloper platform

CircuitNotion developer platform

Build on the CircuitNotion AI API

Create API keys, track usage and fund a prepaid wallet in RWF. Point any OpenAI-compatible client at https://api.circuitnotion.com/v1 and keep the rest of your integration unchanged. The same key works with Anthropic Messages clients such as Claude Code.

Base URL
https://api.circuitnotion.com/v1
Auth
Authorization: Bearer cn_…
Protocols
OpenAI & Anthropic Messages

Quickstart

Send your first request in three steps

  1. Fund your walletSign in and top up credits on the billing dashboard.
  2. Create an API keyGenerate a key in the platform. It starts with cn_ and is shown once.
  3. Call the APIUse the official OpenAI SDKs or plain HTTP against https://api.circuitnotion.com/v1.
cURLbash
curl https://api.circuitnotion.com/v1/chat/completions \
  -H "Authorization: Bearer $CIRCUITNOTION_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "circuit-2-turbo",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Pythonpython
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.circuitnotion.com/v1",
    api_key=os.environ["CIRCUITNOTION_API_KEY"],
)

response = client.chat.completions.create(
    model="circuit-2-turbo",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

In the workspace

Everything you need to ship on the API

API keys

Create, list and revoke keys. Each key has its own requests-per-minute limit and an optional daily RWF spend cap.

Authentication →

Prepaid billing in RWF

Fund a wallet and pay per request. Each generation reserves its estimated maximum cost, then settles on the tokens it actually used.

Billing and limits →

Models and pricing

See the live model catalogue and per-model rates, or query GET /v1/models from your own code.

Models →

Chat, images and embeddings

OpenAI-compatible chat completions, responses, image generation and embeddings, with server-sent-event streaming.

Chat completions →

Structured output and tools

Request JSON that matches a schema, and let models call your functions with OpenAI-style tool calling.

Function calling →

Coding agents

Claude Code, Cline, Roo Code and other terminal agents run on the same key and wallet, over the OpenAI or Anthropic Messages protocol.

Coding agents →