LLMBase | Docs

Integrations

Using via OpenRouter

Access LLMBase models through OpenRouter's unified API gateway.

Updated


OpenRouter is a unified API gateway that routes requests across hundreds of AI providers. LLMBase models are listed on OpenRouter, so you can access them alongside models from OpenAI, Anthropic, Google, and others — using a single OpenRouter API key.

Endpoint

Use OpenRouter’s base URL instead of LLMBase’s:

https://openrouter.ai/api/v1

Model IDs on OpenRouter

OpenRouter model IDs are the same as LLMBase’s unified model IDs:

LLMBase modelOpenRouter model ID
GLM-5zai-org/glm-5
GLM-4zai-org/glm-4

Quick example

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
});

const response = await client.chat.completions.create({
  model: "zai-org/glm-5",
  messages: [{ role: "user", content: "Hello!" }],
});

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

OpenRouter-specific headers

OpenRouter recommends including two optional headers for analytics and abuse prevention:

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
  defaultHeaders: {
    "HTTP-Referer": "https://yourapp.com",   // your site URL
    "X-Title":      "Your App Name",         // shown in OpenRouter dashboard
  },
});

curl

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "HTTP-Referer: https://yourapp.com" \
  -H "X-Title: Your App" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/glm-5",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

When to use OpenRouter vs direct

Direct (api.llmbase.ai)Via OpenRouter
LatencyLower — one fewer hopSlightly higher
BillingBilled directly by LLMBaseBilled by OpenRouter
Key managementSeparate LLMBase keySingle key for all providers
Model switchingLLMBase models onlyAny OpenRouter model
Rate limitsLLMBase limitsOpenRouter limits

Use the direct API when you only need LLMBase models and want the lowest latency. Use OpenRouter when you want a single key and the ability to swap providers without changing code.