Use 200+ AI Models with the OpenAI API Format

Anything built on the OpenAI SDK can talk to every model in the idapt catalog by changing one line: the base URL. Claude, GPT, Gemini, Grok, DeepSeek, Mistral, and the rest of the 200+ model catalog answer at one endpoint, with one key and one bill.

One endpoint, every model

Set your base URL to https://idapt.app/api/openai/v1 and use an idapt API key. Every library and tool that speaks the OpenAI format works unchanged: LangChain, LlamaIndex, editors, custom scripts.

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://idapt.app/api/openai/v1",
    api_key="idapt_your_key_here",
)

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4.6",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://idapt.app/api/openai/v1",
  apiKey: "idapt_your_key_here",
});

const response = await client.chat.completions.create({
  model: "google/gemini-2.5-flash",
  messages: [{ role: "user", content: "Hello!" }],
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

curl

curl https://idapt.app/api/openai/v1/chat/completions \
  -H "Authorization: Bearer idapt_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

What's supported

• Chat Completions: streaming and non-streaming, tool and function calling included.
• Responses API: POST /responses works against the same catalog.
• Model listing: GET /models returns every model with its id.
• Full SSE streaming, compatible with every OpenAI SDK.

Prefer a different dialect? The same catalog answers on an Anthropic-compatible endpoint and an OpenRouter-compatible one, so existing code keeps its SDK. The OpenAI API migration guide maps every field.

Pricing

The same rates as the web app, at the prices shown in the app, with no separate API pricing. On a paid plan, calls draw your included usage first, then your Credit balance (a 9.5% service fee applies when you add credits). Or bring your own provider keys and matching calls bill straight to your provider account.

Get started

1. Sign up and pick a plan, or connect your own keys.
2. Create a key under Settings → API Keys with the completions permission.
3. Set the base URL and ship. The full guide covers models, errors, and limits.