Developers

Quickstart

Waitlist

Three steps: create an account, create a key, and call the endpoint. The first two work today. The endpoint itself is on a waitlist until real capacity is connected — read on for exactly what that means.

1. Create an account and an organisation

Sign up for a personal account, or create a team organisation once you are in. Every account starts on the free waitlist tier; no payment is collected.

2. Create an API key

From your dashboard, create a key and copy it immediately: it is shown once and never stored in a form you can read back. A key is scoped to read the model catalogue, call the inference endpoint, or both, and expires in 90 days by default.

Create a key

3. Call the endpoint

The endpoint is OpenAI-compatible: point any OpenAI SDK at the base URL below, or send the request directly. Read the model id from GET /api/v1/models first — the id below is a placeholder.

curl

curl https://www.cloudfrm.ai/api/v1/inference/chat/completions \
  -H "Authorization: Bearer cfrm_test_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<model_id>",
    "messages": [{ "role": "user", "content": "Say hello." }]
  }'

Python (openai SDK)

from openai import OpenAI

client = OpenAI(
    api_key="cfrm_test_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://www.cloudfrm.ai/api/v1/inference",
)

response = client.chat.completions.create(
    model="<model_id>",
    messages=[{"role": "user", "content": "Say hello."}],
)
print(response.choices[0].message.content)

JavaScript (openai SDK)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "cfrm_test_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
  baseURL: "https://www.cloudfrm.ai/api/v1/inference",
});

const response = await client.chat.completions.create({
  model: "<model_id>",
  messages: [{ role: "user", content: "Say hello." }],
});
const reply = response.choices[0].message.content;

Response (OpenAI shape, plus a cfrm extension)

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "<model_id>",
  "choices": [{ "index": 0, "finish_reason": "stop", "message": { "role": "assistant", "content": "..." } }],
  "usage": { "prompt_tokens": 8, "completion_tokens": 5, "total_tokens": 13 },
  "cfrm": { "request_id": "req_...", "cost_micro_usd": 1234, "usage_source": "upstream" }
}

See the full API reference

What happens today

The account and the key work now. The endpoint itself does not: every call answers 503 with the code platform_waitlist until the owner connects real inference capacity, and the response never claims a model ran. Sign up and create a key today, so you are ready the moment it opens — nothing else about integrating changes when it does.

See live status

Ready to start?

Create an account, or open your dashboard if you already have one.