Glama

Glama AI Gateway

OpenAI-compatible LLM gateway exposing 90+ models from OpenAI, Anthropic, Google, DeepSeek, Mistral, xAI, Moonshot, Alibaba (Qwen), Cohere, and Perplexity behind a single base URL (`https://gateway.glama.ai/v1`). Drop-in replacement for any OpenAI SDK with prompt caching, load balancing, fallbacks, reasoning effort levels, text streaming, web search/fetch tools, real-time cost analytics, consolidated billing, and no rate limits under 1B tokens/day. ~40ms median overhead and 99% uptime SLO.

Glama AI Gateway is one of 7 APIs that Glama publishes on the APIs.io network.

Tagged areas include AI, Artificial Intelligence, LLM Gateway, OpenAI Compatible, and Multi-Provider. The published artifact set on APIs.io includes API documentation.

GitHub

Documentation

📖
Documentation
https://glama.ai/ai/gateway
📖
Documentation
https://glama.ai/ai/models

Other Resources

🔗
BaseURL
https://gateway.glama.ai/v1

API entry from apis.yml

apis.yml Raw ↑ 
aid: glama-ai:glama-ai-gateway
name: Glama AI Gateway
tags:
- AI
- Artificial Intelligence
- LLM Gateway
- OpenAI Compatible
- Multi-Provider
humanURL: https://glama.ai/ai/gateway
baseURL: https://gateway.glama.ai/v1
properties:
- url: https://glama.ai/ai/gateway
  type: Documentation
- url: https://glama.ai/ai/models
  type: Documentation
- url: https://gateway.glama.ai/v1
  type: BaseURL
description: OpenAI-compatible LLM gateway exposing 90+ models from OpenAI, Anthropic, Google, DeepSeek,
  Mistral, xAI, Moonshot, Alibaba (Qwen), Cohere, and Perplexity behind a single base URL (`https://gateway.glama.ai/v1`).
  Drop-in replacement for any OpenAI SDK with prompt caching, load balancing, fallbacks, reasoning effort
  levels, text streaming, web search/fetch tools, real-time cost analytics, consolidated billing, and
  no rate limits under 1B tokens/day. ~40ms median overhead and 99% uptime SLO.