curl https://modelport.tech/v1/chat/completions \
-H "Authorization: Bearer mp_live_your_key_here" \
-H "Content-Type: application/json" \
-d '{"model":"cx/gpt-5.6-sol","messages":[{"role":"user","content":"Reply with ModelPort connected."}]}'Public quick start
From signup to first request
Create an account, add prepaid balance, generate dedicated setup credentials, and run one verified request. Your full key is shown only when created.
01
Verify account
02
Add balance
03
Create credentials
04
Send request
pip install openai
from openai import OpenAI
client = OpenAI(
api_key="mp_live_your_key_here",
base_url="https://modelport.tech/v1",
)
response = client.chat.completions.create(
model="cx/gpt-5.6-sol",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)npm install openai
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "mp_live_your_key_here",
baseURL: "https://modelport.tech/v1",
});
const response = await client.chat.completions.create({
model: "cx/gpt-5.6-sol",
messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);Coding agents
OpenCode
Verified
Create an OpenCode connection in Connect an app. The generated command includes your new key and all enabled text models.
Codex CLI
Verified
Create a Codex CLI connection. ModelPort generates an isolated Responses API profile without changing your default provider.
Common API responses
401The key is missing, incomplete, or revoked. Create or replace credentials.
402The setup is valid, but the account needs prepaid balance.
429The key exceeded its configured requests-per-minute limit.
400 · modelThe model ID is unknown or currently disabled. Choose an enabled catalog model.
5xxThe provider or gateway is temporarily unavailable. Retry after a short delay.