Skip to content
  12.  
    13. © 2023 – 2025 OpenRouter, Inc

    One API, any LLM, any provider

    Plans for AI native startups, indie hackers and enterprises.

    Get StartedTalk to sales
    Model Prices →API Docs →

    OpenRouter Pricing Plans

    FreePay-as-you-goEnterprise
    Platform FeesN/A5.5%Bulk discounts available
    ModelsExplore all models →25+ free models300+ models300+ models
    ProvidersExplore all models →4 free providers60+ providers60+ providers
    Chat and API AccessTry chat now →
    Activity Logs & Export
    Auto-routing, preferred vendor selectionsLearn more →
    Budgets & Spend Controls
    Prompt CachingLearn more →
    Provisioning API keyLearn more →
    Admin ControlsEnterprise features →
    ZDR & No Training PoliciesModel & provider policy data
    Managed Policy EnforcementZDR policies
    Provider Data Explorer
    SSO/SAML
    Contractual SLAs
    Payment optionsCredit card, crypto & moreInvoicing options
    BYOK LimitsLearn more →1M free reqs/month, 5% fee after5M free reqs/month; custom pricing
    Rate limits50 reqs/dayHigh global limitsOptional dedicated limits
    Token PricingFree models onlyNo minimum spend. Prices based on modelsVolume commitments. Prices based on models
    SupportCommunity SupportEmail SupportSupport SLA with Shared Slack Channel
    Get started for freeBuy CreditsContact Enterprise
    Get started for freeBuy CreditsContact Enterprise

    Frequently Asked Questions

    Billing and Pricing

    How are tokens billed?
    Input and output tokens are billed per model at posted rates.
    Do you mark up provider pricing?
    We do not mark up provider pricing. Pricing shown in the model catalog is what you pay which is exactly what you will see on provider's websites.
    How is billing structured for BYOK, Pay‑As‑You‑Go vs Enterprise?

    Pay-as-you-go: You buy credits and use them as you wish. You can automatically top-up your account or do it manually. You can see the activity in your settings > API Keys

    Enterprise: Pricing is based on volume, prepayment credits, annual commits, and many other factors.

    Are failed or fallback attempts billed?
    No. When routing/fallback is enabled, you're billed only for the successful model run.
    Do you offer volume discounts or annual plans?
    Yes. We support prepayment credits, volume discounts, annual commits, and invoicing/POs.
    Are streaming responses billed differently?
    No. Pricing is per token regardless of streaming. You pay only for successful runs when routing/fallback is enabled.
    What payment methods do you accept?
    Pay-as-you-go accepts credit/debit cards, crypto, and bank transfers. Enterprise supports invoicing and POs. Contact Sales for procurement options.
    Are taxes (VAT/GST) included in prices?
    Prices are exclusive of applicable taxes. Where required, VAT/GST may be added on invoices.
    Is there a minimum spend or lock‑in on Pay-as-you-go?
    No. Pay-as-you-go has no minimums and no lock‑in. You pay only for what you use.

    Usage and Rate Limits

    Do you enforce rate limits?

    For free plan - Yes. Not for Pay-as-you-go or Enterprise plans.

    Yes. Different plans have different limits.

    • Free users have a limit of 50 requests per day and 20 requests per minute (rpm)
    • For pay-as-you-go users with at least $10 in credits -
      • No limits on paid models
      • 1000 request limit on free models with 20 RPM

    Free‑tier usage of popular models can be subject to rate limiting by the provider, especially during peak times. Failed attempts still count toward your daily quota.

    Can I separate environments (dev/staging/production)?
    Yes. Create separate API keys per environment with their own caps, alerts, and activity logs.
    Do you enforce platform rate limits?
    No, there are no platform‑level rate limits for Pay-as-you-go or Enterprise users. Free users have rate limits.

    Routing and Latency

    Can I make sure to send API requests in specific regions?
    Yes. Regional routing is available on Enterprise and Pay-as-you-go plans.
    Does routing affect latency?
    Routing improves reliability; latency may vary by model/provider/region. If you need consistent latency, pin a specific model and region.
    What happens if a model is deprecated or pricing changes?

    If a model is deprecated, you will receive a 404 when you request it, with an error message like "no endpoints for this model found."

    If the pricing changes, we will continue to route to the model and it will serve your requests. But, you will be charged at the new rate and your credits will deduct accordingly. This will be reflected in your billing.

    Can I pin specific model versions?
    Yes. Choose an explicit model ID/version to avoid unexpected changes. You can also switch models without changing your integration.

    Privacy and Security

    Do you train on customer data?
    No. We do not train on your data. Provider‑side retention can be disabled at the account level or per API call.
    Do you support SSO?
    Yes. SSO (SAML) is available on Enterprise plans; contact us to enable it on your account.

    Models and Features

    How do I migrate from OpenAI/Anthropic?
    Our API is OpenAI‑compatible. Update the base URL and model names; see Quickstart.
    Do you support function calling/tools?
    If the underlying model supports tools/function calling, you can use it through the same API. See the API reference for examples.

    Reliability and Uptime

    What happens if a provider is down or a model errors?
    Routing/fallback can automatically try alternative models. You're billed only for the successful runs. Every request has Zero Completion Insurance.
    Where can I check uptime and incidents?
    Visit the status page for real‑time uptime and incident history.

    Ready to get started?

    Join thousands of developers building with OpenRouter

    Start FreeContact Sales