Quickstart
FlowAPI is a unified model API for teams that want one integration across multiple models, with built-in Playground, API keys, billing, and model discovery.
1. Sign in to FlowAPI
Create an account or sign in at flowapi.net . Once signed in, you can access the Console, browse models, use the Playground, and generate API keys.
Start in the browser first, then move to SDK or REST API calls when you are ready to integrate.
2. Browse models and pricing
Visit the Models page to review currently available models, pricing, context length, and capabilities. This is the fastest way to decide which model fits your workload.
When evaluating models, compare:
- reasoning quality
- context window
- latency
- input and output price
- modality support
3. Try the Playground
Open the Playground to test prompts, compare outputs, and validate parameters before writing application code.
Typical Playground workflow:
- Select a model.
- Enter your prompt or conversation messages.
- Tune parameters such as
temperatureandmax_tokens. - Run the request and review the output.
4. Create an API key
Go to the API Keys page and create a key for your application. You will need this key to authenticate all API requests.
Store your API key as an environment variable such as FLOW_API_KEY. Never commit API keys to version control or expose them in browser-side code.
5. Install a client
FlowAPI is OpenAI-compatible, so you can use the standard OpenAI SDK in most applications.
Python
pip install openaiNode.js
npm install openaicURL
curl --version6. Send your first request
Python
from openai import OpenAI
client = OpenAI(
api_key="YOUR_FLOW_API_KEY",
base_url="https://api.flowapi.net/v1"
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello, what can you do?"}
],
temperature=0.7,
max_tokens=1024
)
print(response.choices[0].message.content)Node.js
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "YOUR_FLOW_API_KEY",
baseURL: "https://api.flowapi.net/v1",
});
const response = await client.chat.completions.create({
model: "gpt-4o",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Hello, what can you do?" },
],
temperature: 0.7,
max_tokens: 1024,
});
console.log(response.choices[0].message.content);cURL
curl https://api.flowapi.net/v1/chat/completions \
-H "Authorization: Bearer YOUR_FLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [
{ "role": "system", "content": "You are a helpful assistant." },
{ "role": "user", "content": "Hello, what can you do?" }
]
}'7. Stream responses
For longer outputs, enable streaming so tokens arrive as soon as they are generated.
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "user", "content": "Write a haiku about programming."}
],
stream=True
)
for chunk in response:
if not chunk.choices:
continue
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)