The LiteLLM alternative:
managed, observable, EU-ready

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "aws/claude-opus-5-5",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);

1import Anthropic from "@anthropic-ai/sdk";
2
3const client = new Anthropic({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const message = await client.messages.create({
9  model: "aws/claude-opus-5-5",
10  max_tokens: 1024,
11  messages: [{ role: "user", content: "Hello" }],
12});
13console.log(message.content);

1import { GoogleGenAI } from "@google/genai";
2
3const ai = new GoogleGenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
6});
7
8const response = await ai.models.generateContent({
9  model: "vertexai/gemini-3.8-flash-eu",
10  contents: "Hello",
11});
12console.log(response.text);

1import { createOpenAI } from "@ai-sdk/openai";
2import { generateText } from "ai";
3
4const opper = createOpenAI({
5  apiKey: process.env.OPPER_API_KEY,
6  baseURL: "https://api.opper.ai/v3/compat",
7});
8
9const { text } = await generateText({
10  model: opper("aws/claude-opus-5-5"),
11  prompt: "Hello",
12});

1import { ChatOpenAI } from "@langchain/openai";
2
3const llm = new ChatOpenAI({
4  model: "aws/claude-opus-5-5",
5  apiKey: process.env.OPPER_API_KEY,
6  configuration: {
7    baseURL: "https://api.opper.ai/v3/compat",
8  },
9});
10
11const response = await llm.invoke("Hello");

1# Route Claude Code through Opper, no install
2npx @opperai/cli launch claude
3
4# Or wire it up by hand
5export ANTHROPIC_BASE_URL="https://api.opper.ai/v3/compat"
6export ANTHROPIC_AUTH_TOKEN="$OPPER_API_KEY"

1# Run OpenCode on Opper, no install
2npx @opperai/cli launch opencode
3
4# Pin any of 700+ models
5npx @opperai/cli launch opencode --model glm-5.3-flash

1// ~/.openclaw/openclaw.json
2{
3  models: {
4    mode: "merge",
5    providers: {
6      "opper": {
7        baseUrl: "https://api.opper.ai/v3/compat",
8        apiKey: "YOUR_OPPER_API_KEY",
9        api: "openai-completions",
10      }
11    }
12  }
13}

1// Cursor Settings > Models
2
3Override OpenAI Base URL:
4  https://api.opper.ai/v3/compat
5
6OpenAI API Key:
7  YOUR_OPPER_API_KEY
8
9Models:
10  aws/claude-opus-5-5
11  azure:eu/gpt-6-sol