Use AI in your apps.

1. Get the three values

   Base URLhttps://api.ompera.net/v1Copy

   API keyCreate one in Workspace → API keys.

   ModelCopy an address from Workspace → Models: your own (my/local), one from your pools (HomeLab/qwen3-4b) or one from the Ompera network.

   Turn on Allow Unshielded models when you create the key to use models connected from a computer, yours or from your pools. Ompera network models work with any key.

2. Paste them into your app

   In the examples, replace MODEL_ADDRESS with your model address.

   Any appOpenCodePythonJavaScriptFrameworkscurl

   Any app

   Look for OpenAI-compatible, custom provider or base URL in the app's settings and enter the three values. Choose the Chat Completions API if asked; the newer Responses API is not supported yet.

   Apps with a model picker read the list from GET /v1/models; in others, type the model address. Tools built on the OpenAI SDK often read the OPENAI_BASE_URL and OPENAI_API_KEY environment variables: set them to the base URL and your Ompera key.

   OpenCode

   Save as opencode.json in your project (or merge into ~/.config/opencode/opencode.json), set OMPERA_API_KEY in your environment and pick the Ompera model in OpenCode.

   {
     "$schema": "https://opencode.ai/config.json",
     "provider": {
       "ompera": {
         "npm": "@ai-sdk/openai-compatible",
         "name": "Ompera",
         "options": {
           "baseURL": "https://api.ompera.net/v1",
           "apiKey": "{env:OMPERA_API_KEY}"
         },
         "models": { "MODEL_ADDRESS": { "name": "Ompera model" } }
       }
     }
   }

   Copy

   Python

   With the official OpenAI SDK (pip install openai).

   import os
   from openai import OpenAI
   
   client = OpenAI(base_url="https://api.ompera.net/v1", api_key=os.environ["OMPERA_API_KEY"])
   reply = client.chat.completions.create(
       model="MODEL_ADDRESS",
       messages=[{"role": "user", "content": "Hello!"}],
   )
   print(reply.choices[0].message.content)

   Copy

   To show the answer while it's written, add stream=True (example).

   JavaScript

   With the official OpenAI SDK (npm install openai).

   import OpenAI from "openai";
   
   const client = new OpenAI({ baseURL: "https://api.ompera.net/v1", apiKey: process.env.OMPERA_API_KEY });
   const reply = await client.chat.completions.create({
     model: "MODEL_ADDRESS",
     messages: [{ role: "user", content: "Hello!" }],
   });
   console.log(reply.choices[0].message.content);

   Copy

   To show the answer while it's written, add stream: true (example).

   Frameworks

   LangChain (pip install langchain-openai):

   import os
   from langchain_openai import ChatOpenAI
   
   llm = ChatOpenAI(model="MODEL_ADDRESS", base_url="https://api.ompera.net/v1", api_key=os.environ["OMPERA_API_KEY"])
   print(llm.invoke("Hello!").content)

   Copy

   Vercel AI SDK (npm install ai @ai-sdk/openai-compatible):

   import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
   import { generateText } from "ai";
   
   const ompera = createOpenAICompatible({ name: "ompera", baseURL: "https://api.ompera.net/v1", apiKey: process.env.OMPERA_API_KEY });
   const { text } = await generateText({ model: ompera("MODEL_ADDRESS"), prompt: "Hello!" });
   console.log(text);

   Copy

   curl

   A quick check from the terminal.

   curl https://api.ompera.net/v1/chat/completions \
     -H "Authorization: Bearer $OMPERA_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{"model":"MODEL_ADDRESS","messages":[{"role":"user","content":"Hello!"}]}'

   Copy

   List the models your key can use: curl https://api.ompera.net/v1/models -H "Authorization: Bearer $OMPERA_API_KEY"

   Your app gets answers from the model.

Need translation, text from images, speech to text or embeddings? They are separate services: same key; embeddings use a fixed engine for your search index.

Got an error? See what each error means.