Fast, Reliable AI Gateway

Connect to 100+ AI models using an OpenAI compatible API.

Low latency

~40ms globally

No hidden fees

Pay listed prices

99% uptime

Status

OpenAI compatible API

Connect, load balance, setup fallbacks and seamlessly manage 100+ AI models using an OpenAI compatible API.

import { OpenAI } from 'openai'

const openai = new OpenAI({
  baseURL: 'https://glama.ai/api/gateway/openai/v1',
  apiKey: GLAMA_API_KEY,
});

await openai.chat.completions.create({
  messages: [
    {
      role: 'user',
      content: 'Hello!'
    }
  ],
  model: 'anthropic/claude-2',
});

Benefit from our globally distributed infrastructure, low latency, transparent pricing, no rate limits, built-in caching, logging and consolidated billing.

Real-Time API Cost Insights

Get real-time visibility into your API costs with detailed analytics of token consumption, cache performance, and overall expenditure.

Complete Transparency with Detailed Logs

Every API interaction is logged, allowing you to track spending, audit usage, implement guardrails, and troubleshoot issues. Easily export logs to JSON format.

Get your API key

Which AI models are supported?

Does Glama support OAuth PKCE?

What are the rate limits?

How is Glama Gateway different from OpenRouter?

Have questions?

Join our Discord