Skip to main content

​
Vercel AI SDK

npm install ai @ai-sdk/openai

import { createOpenAI } from "@ai-sdk/openai";
import { generateText, streamText } from "ai";

const orchid = createOpenAI({
  baseURL: "https://llm.orchid.ac/v1",
  apiKey:  process.env.ORCHID_API_KEY!,
});

const { text } = await generateText({
  model:  orchid("orchid01"),
  prompt: "Summarise this 10-K filing...",
});

​
Streaming in Next.js

import { streamText }    from "ai";
import { createOpenAI }  from "@ai-sdk/openai";

const orchid = createOpenAI({
  baseURL: "https://llm.orchid.ac/v1",
  apiKey:  process.env.ORCHID_API_KEY!,
});

export async function POST(req: Request) {
  const { messages } = await req.json();

  const result = streamText({
    model:    orchid("orchid01"),
    messages,
  });

  return result.toDataStreamResponse();
}

​
LiteLLM

LiteLLM can treat Orchid as an OpenAI-compatible proxy: 
import litellm

response = litellm.completion(
    model="openai/orchid01",
    api_base="https://llm.orchid.ac/v1",
    api_key="orchid-your-key-here",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
The openai/ prefix tells LiteLLM to use the OpenAI-compatible path. The model name after the prefix (orchid01) is passed to the API.