Recommended endpoints
Minimal request
{
"model": "gpt-4.1",
"input": "Get today's Shanghai weather.",
"tools": [
{
"type": "function",
"name": "get_weather",
"description": "Fetch weather",
"parameters": {
"type": "object",
"properties": {
"city": { "type": "string" }
},
"required": ["city"]
}
}
]
}
cURL example
curl https://maas.apigo.ai/v1/responses \
-H "Authorization: Bearer $YOUR API KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4.1",
"input": "Get today's Shanghai weather.",
"tools": [
{
"type": "function",
"name": "get_weather",
"description": "Fetch weather",
"parameters": {
"type": "object",
"properties": {
"city": { "type": "string" }
},
"required": ["city"]
}
}
]
}'
Python example
from openai import OpenAI
client = OpenAI(
base_url="https://maas.apigo.ai/v1",
api_key="<YOUR API KEY>",
)
response = client.responses.create(
model="gpt-4.1",
input="Get today's Shanghai weather.",
tools=[
{
"type": "function",
"name": "get_weather",
"description": "Fetch weather",
"parameters": {
"type": "object",
"properties": {
"city": {"type": "string"},
},
"required": ["city"],
},
}
],
)
print(response.output)
Node.js example
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://maas.apigo.ai/v1",
apiKey: process.env.YOUR API KEY,
});
const response = await client.responses.create({
model: "gpt-4.1",
input: "Get today's Shanghai weather.",
tools: [
{
type: "function",
name: "get_weather",
description: "Fetch weather",
parameters: {
type: "object",
properties: {
city: { type: "string" }
},
required: ["city"]
}
}
]
});
console.log(response.output);
Best practices
- Keep function schemas explicit and strict
- Do not assume there will be only one tool call
- Persist the raw tool calls and tool results for replay and debugging