The largest AI gateway: a unified, OpenAI-compatible API for 400+ LLMs from 70+ providers (100T tokens/month, 10M+ users).

OpenRouter is the largest AI gateway — a platform aggregating access to 400+ language models from over 70 inference providers (OpenAI, Anthropic, Google, Meta, Mistral, xAI, Cohere, Together, Fireworks, Groq, Cerebras and many others) behind a single OpenAI-compatible API. Founded in early 2023 as the first LLM marketplace, it now serves 100 trillion tokens per month and over 10 million users (as of June 2026).
Eliminate vendor lock-in: switch model or provider without changing code (just change the model name in the request). Automatic failover between providers on outages. Better pricing through aggregated demand and competition among providers. Per-query routing (OpenRouter Fusion) — model selection by price, latency and quality.
Main product: API gateway (OpenAI-compatible REST + streaming). Additionally: OpenRouter Chat (browser chat UI), OpenRouter Fusion (multi-model routing), OpenRouter Rankings (public leaderboard of top-token models), OpenRouter Apps (registry of apps built on the platform), OpenRouter Labs (research experiments), OpenRouter Enterprise (SSO, SLA, access control).
Two VC rounds: $40M Series A in 2024 (a16z, Menlo Ventures, Sequoia Capital) and $113M Series B on May 26, 2026 led by CapitalG (Alphabet's investment arm). Over $153M in total external funding. Business model: a per-token margin (typically 5%) added on top of providers' raw prices.
Pricing models
Resource quotas
SLA & Support