Skip to content

    The UnifiedInterface For LLMs
    The Unified
    Interface For LLMs

    Better prices, better uptime, no subscription.

    20T

    Monthly Tokens

    4.2M+

    Global Users

    60+

    Active Providers

    500+

    Models

    1

    Signup

    Create an account to get started. You can set up an org for your team later.

    Google
    GitHub
    MetaMask
    2

    Buy credits

    Credits can be used with any model or provider.

    Apr 1
    $99
    Mar 30
    $10
    3

    Get your API key

    Create an API key and start making requests. Fully OpenAI compatible.

    OPENROUTER_API_KEY
    ••••••••••••••••
    Favicon for microsoft
    Favicon for nvidia
    Favicon for meta-llama
    Favicon for google
    Favicon for amazon
    Favicon for deepseek
    Favicon for qwen
    Favicon for moonshotai
    Favicon for minimax
    Favicon for z-ai
    Favicon for mistralai
    Favicon for anthropic
    Favicon for openai
    Favicon for google ai studio
    Favicon for x-ai
    Favicon for cohere
    Favicon for huggingface
    Favicon for perplexity
    Favicon for nousresearch
    Favicon for together
    Favicon for morph
    Favicon for inflection
    Favicon for liquid
    Favicon for inception
    Favicon for arcee-ai

    One API for Any Model

    Access all major models through a single, unified interface. OpenAI SDK works out of the box.

    Browse all
    anthropic/claude-3.7-sonnet
    Model routing visualization
    Favicon for google
    Favicon for anthropic
    Favicon for amazon

    Higher Availability

    Reliable AI models via our distributed infrastructure. Fall back to other providers when one goes down.

    Learn more
    Performance graphPerformance graph

    Price and Performance

    Keep costs in check without sacrificing speed. OpenRouter runs at the edge, adding just ~25ms between your users and their inference.

    Learn more
    Data policy visualization

    Custom Data Policies

    Protect your organization with fine grained data policies. Ensure prompts only go to the models and providers you trust.

    View docs

    Explore Models

    Discover AI models across our collection, from all major labs and providers.

    View models

    Model & App Rankings

    Explore token usage across models, labs, and public applications.

    View rankings
  1.  
  2. © 2023 – 2025 OpenRouter, Inc
    Routing Curves
    Routing Curves

    Gemini 2.5 Pro

    Favicon for google
    by google

    178.7B

    Tokens/wk

    2.8s

    Latency

    +1.95%

    Weekly growth

    Featured Models

    View Trending

    Featured Models

    Gemini 2.5 Pro

    Favicon for google
    by google

    178.7B

    Tokens/wk

    2.8s

    Latency

    +1.95%

    Weekly growth

    GPT-5

    Favicon for openai
    by openai

    75.9B

    Tokens/wk

    10.0s

    Latency

    -3.18%

    Weekly growth

    Claude Sonnet 4.5

    Favicon for anthropic
    by anthropic

    609.7B

    Tokens/wk

    1.9s

    Latency

    +10.65%

    Weekly growth

    Recent Announcements

    View all

    Is Implicit Caching Prompt Retention?

    Should customers consider providers that have implicit caching as “ZDR”?

    10/23/2025New

    Provider Variance: Introducing Exacto

    Does the same model perform differently across different providers?

    10/21/2025New

    1 million free BYOK requests per month

    Every customer gets 1,000,000 “Bring Your Own Key” (BYOK) requests per month for free.

    10/1/2025