SDKs & Libraries

DeployAI is OpenAI-compatible. Use any OpenAI client library — just change the base URL.

No custom SDK required. Since DeployAI implements the OpenAI API format, you can use the official OpenAI SDKs, the Vercel AI SDK, or any OpenAI-compatible library. Just point it at https://api.deployai.dev/v1.

Client Libraries

TypeScript / JavaScript

Package: openai

Docs

$ npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.deployai.dev/v1",
  apiKey: process.env.DEPLOYAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "openai/gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});

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

Python

Package: openai

Docs

$ pip install openai

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.deployai.dev/v1",
    api_key=os.environ["DEPLOYAI_API_KEY"],
)

completion = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

Vercel AI SDK

Package: @ai-sdk/openai

Docs

$ npm install ai @ai-sdk/openai

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

const deployai = createOpenAI({
  baseURL: "https://api.deployai.dev/v1",
  apiKey: process.env.DEPLOYAI_API_KEY,
});

const result = streamText({
  model: deployai("anthropic/claude-3.5-sonnet"),
  prompt: "Explain quantum computing simply",
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

cURL

curl https://api.deployai.dev/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DEPLOYAI_API_KEY" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Framework Integrations

DeployAI works seamlessly with popular AI frameworks.

LangChain

Use DeployAI as a drop-in OpenAI replacement in LangChain pipelines.

Python

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.deployai.dev/v1",
    api_key="sk-your-key",
    model="anthropic/claude-3.5-sonnet",
)

response = llm.invoke("What is the meaning of life?")
print(response.content)

LlamaIndex

Connect DeployAI to LlamaIndex for RAG and document Q&A.

Python

from llama_index.llms.openai import OpenAI

llm = OpenAI(
    api_base="https://api.deployai.dev/v1",
    api_key="sk-your-key",
    model="openai/gpt-4o",
)

response = llm.complete("Summarize this document...")
print(response)

Bring Your Own Key (BYOK)

Already have API keys from providers like OpenAI or Anthropic? You can use them directly through DeployAI for centralized routing, logging, and failover — without paying a markup on tokens.

Configure BYOK from your dashboard settings.