Provider pricing

OpenRouter AI API pricing

OpenRouter is a unified inference gateway that proxies 300+ models from every major lab and inference provider behind a single OpenAI-compatible API. Pricing matches upstream rates with a small markup (often offset by free-tier credits and provider promos), and built-in routing automatically falls back to a healthy provider when one is rate-limited or down.

Founded2023
HeadquartersSan Francisco, CA
Tracked models1

Best for

Teams that want one integration to test, route, and cost-optimize across the entire LLM market.

Strengths

  • Single API + key for 300+ models across every major provider
  • Automatic provider fallback and load-balancing for high uptime
  • Per-request provider preference, price ceiling, and latency routing
  • Free-tier credits + frequent promo pricing on top open-weight models

Tracked OpenRouter models

ModelInput $/MOutput $/MContextTierBest for
Owl Alpha$0$01,048,756FlagshipFree alpha — high-performance agentic foundation model with native tool use and ~1.05M context. Prompts/completions may be logged.