Back to OmniaKey

OpenAI

en-api-openai-compatible.md

latest2.2 KB
Original Source

Use the OpenAI-compatible base URL for OpenAI SDKs, Cursor, Codex, Cline, aider, and most custom tools:

https://api.omniakey.com/v1

Chat Completions

POST /v1/chat/completions is the most portable endpoint. It can call supported Claude, GPT, Gemini, and Grok models by id.

cURL

Python

TypeScript

curl https://api.omniakey.com/v1/chat/completions \
  -H "Authorization: Bearer your-omniakey-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "messages": [{"role": "user", "content": "Refactor this function for readability."}]
  }'
from openai import OpenAI

client = OpenAI(
    api_key="your-omniakey-api-key",
    base_url="https://api.omniakey.com/v1",
)

response = client.chat.completions.create(
    model="claude-opus-4-8",
    messages=[{"role": "user", "content": "Refactor this function for readability."}],
)

print(response.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your-omniakey-api-key",
  baseURL: "https://api.omniakey.com/v1",
});

const response = await client.chat.completions.create({
  model: "claude-opus-4-8",
  messages: [{ role: "user", content: "Refactor this function for readability." }],
});

console.log(response.choices[0].message.content);

Responses

POST /v1/responses follows OpenAI’s newer Responses shape and serves GPT models. Use it for Codex-style GPT workflows. For Claude, Gemini, or Grok, use Chat Completions unless your tool explicitly requires a different protocol.

curl https://api.omniakey.com/v1/responses \
  -H "Authorization: Bearer your-omniakey-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": "Refactor this function for readability."
  }'

POST /v1/responses/compact is available for clients that call the Responses compaction path, including Codex-style context compaction flows.

Models

Use GET /v1/models for an OpenAI-compatible model list. For the human-readable catalog, see Supported Models.

AuthenticationAnthropic-native API

⌘I