Lightning AI

Lightning AI Model APIs

Hosted inference API that serves frontier and open models behind a Lightning API key, billed per token with a free monthly token allowance. Accessible through the litai Python client and through OpenAI- and Anthropic-compatible client configuration, with per-plan requests-per-minute and tokens-per-minute limits.

GitHub

Documentation

📖
Documentation
https://lightning.ai/docs/platform/inference/model-apis
📖
RateLimits
https://raw.githubusercontent.com/api-evangelist/lightning-ai/refs/heads/main/rate-limits/lightning-ai-rate-limits.yml

Other Resources

🔗
Models
https://lightning.ai/models

API entry from apis.yml

apis.yml Raw ↑ 
aid: lightning-ai:model-apis
name: Lightning AI Model APIs
description: Hosted inference API that serves frontier and open models behind a Lightning API key, billed
  per token with a free monthly token allowance. Accessible through the litai Python client and through
  OpenAI- and Anthropic-compatible client configuration, with per-plan requests-per-minute and tokens-per-minute
  limits.
humanURL: https://lightning.ai/docs/platform/inference/model-apis
baseURL: https://lightning.ai
tags:
- Inference
- LLM
- Model APIs
- Tokens
properties:
- type: Documentation
  url: https://lightning.ai/docs/platform/inference/model-apis
- type: RateLimits
  url: rate-limits/lightning-ai-rate-limits.yml
- type: Models
  url: https://lightning.ai/models