SDKs & Libraries
LLM Hub is compatible with all OpenAI SDKs. Simply change the base URL to start using our API with your preferred language.
No Special SDK Required
LLM Hub implements the OpenAI API specification, so you can use the official OpenAI SDK for your language. Just set the base URL tohttps://api.llmhub.one/v1and use your LLM Hub API key.
Available SDKs
JavaScript / TypeScript
OfficialPackage:
openaiInstallation
Bash
npm install openaiConfiguration
Java
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.llmhub.one/v1',
apiKey: process.env.LLMHUB_API_KEY
});Python
OfficialPackage:
openaiInstallation
Bash
pip install openaiConfiguration
Python
from openai import OpenAI
client = OpenAI(
base_url="https://api.llmhub.one/v1",
api_key="your-api-key"
)Go
OfficialPackage:
github.com/openai/openai-goInstallation
Bash
go get github.com/openai/openai-goConfiguration
Go
import (
"github.com/openai/openai-go"
"github.com/openai/openai-go/option"
)
client := openai.NewClient(
option.WithBaseURL("https://api.llmhub.one/v1"),
option.WithAPIKey(os.Getenv("LLMHUB_API_KEY")),
)PHP
CommunityPackage:
openai-php/clientInstallation
Bash
composer require openai-php/clientConfiguration
PHP
use OpenAI;
$client = OpenAI::factory()
->withBaseUri('https://api.llmhub.one/v1')
->withApiKey($_ENV['LLMHUB_API_KEY'])
->make();Ruby
CommunityPackage:
ruby-openaiInstallation
Bash
gem install ruby-openaiConfiguration
Ruby
require "openai"
client = OpenAI::Client.new(
uri_base: "https://api.llmhub.one/v1",
access_token: ENV["LLMHUB_API_KEY"]
)C# / .NET
OfficialPackage:
OpenAIInstallation
Bash
dotnet add package OpenAIConfiguration
C#
using OpenAI;
var client = new OpenAIClient(
new OpenAIClientOptions {
BaseUrl = new Uri("https://api.llmhub.one/v1"),
ApiKey = Environment.GetEnvironmentVariable("LLMHUB_API_KEY")
});Java / Kotlin
OfficialPackage:
com.openai:openai-javaInstallation
Bash
// Add to build.gradle or pom.xmlConfiguration
Java
import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://api.llmhub.one/v1")
.apiKey(System.getenv("LLMHUB_API_KEY"))
.build();Rust
CommunityPackage:
async-openaiInstallation
Bash
cargo add async-openaiConfiguration
rust
use async_openai::{Client, config::OpenAIConfig};
let config = OpenAIConfig::new()
.with_api_base("https://api.llmhub.one/v1")
.with_api_key(std::env::var("LLMHUB_API_KEY")?);
let client = Client::with_config(config);Direct HTTP / REST
If there's no SDK for your language, you can make direct HTTP requests:
Bash
curl https://api.llmhub.one/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LLMHUB_API_KEY" \
-d '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello!"}]
}'API Endpoints
POST
/v1/chat/completions— Chat & completionsPOST
/v1/images/generations— Image generationPOST
/v1/embeddings— Text embeddingsGET
/v1/models— List available modelsFramework Integrations
LLM Hub works with popular AI frameworks:
LangChain
Use our endpoint with LangChain's ChatOpenAI:
Python
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
base_url="https://api.llmhub.one/v1",
api_key="your-key",
model="gpt-4o"
)Vercel AI SDK
Works with the OpenAI provider:
TypeScript
import { createOpenAI } from '@ai-sdk/openai';
const llmhub = createOpenAI({
baseURL: 'https://api.llmhub.one/v1',
apiKey: process.env.LLMHUB_API_KEY
});LlamaIndex
Configure as an OpenAI-compatible endpoint:
Python
from llama_index.llms.openai import OpenAI
llm = OpenAI(
api_base="https://api.llmhub.one/v1",
api_key="your-key",
model="gpt-4o"
)AutoGen
Use in your AutoGen config:
Python
config_list = [{
"model": "gpt-4o",
"base_url": "https://api.llmhub.one/v1",
"api_key": "your-key"
}]