OpenRouter pricing
Pricing
Plans for indie hackers, AI native startups, growing teams, and enterprises
| Feature | Free |
|---|---|
| Platform fees | N/A |
| ModelsExplore all models → | 25+ free models |
| ProvidersExplore all models → | 4 free providers |
| Chat and API AccessTry chat now → | Yes |
| Activity logs & export | Yes |
| Auto-routing, preferred vendor selectionsLearn more → | No |
| Budgets & Spend Controls | No |
| Advanced notificationsLearn more → | No |
| Prompt CachingLearn more → | No |
| Management API keyLearn more → | No |
| Admin ControlsEnterprise features → | No |
| Data Policy-Based RoutingModel & provider policies | No |
| EU in-region routingLearn more → | No |
| US in-region routingLearn more → | No |
| Workload Identity FederationLearn more → | No |
| Workspace limitLearn more → | 5 |
| DPA | Via Terms of Service |
| Managed Policy Enforcement | No |
| SSO/SAML | No |
| Contractual SLAs | No |
| Payment options | No |
| BYOK LimitsLearn more → | No |
| Rate limits | 50 requests/day |
| Support | Community support |
Frequently Asked Questions
Billing and Pricing
Input and output tokens are billed per model at posted rates.
No. Inference is billed at the provider's list price on every plan. OpenRouter's fee is charged when you buy credits, 5.5% on Standard and 8% on Business, never on individual requests.
Standard and Business: you buy credits, manually or with auto top-up, and each request deducts its cost from your balance. The only billing difference between the two is the fee on credit purchases, 5.5% on Standard and 8% on Business.
Enterprise: pricing is set by contract and based on volume, prepaid credits and annual commitments, with invoicing.
BYOK: the provider bills you for inference directly. Standard and Business include $25,000 of list-price inference per month through BYOK with no OpenRouter fee; Enterprise allowances are custom. Above the allowance, OpenRouter charges 5% of what the same request would cost at list price on OpenRouter, deducted from your credits.
No. An attempt that errors is not charged for its model tokens, so with fallback you pay only for the run that answers. Under Zero Completion Insurance the same holds for a response that returns nothing and no finish reason; auxiliary services that already ran, such as web search or file parsing, may still be billed. Routing through openrouter/auto adds no fee; you pay the rate of whichever model serves the request.
We offer discounted OpenRouter fees in our enterprise plan. We do not discount inference.
No. Pricing is per token whether or not you stream.
Standard and Business: credit and debit cards, AliPay, and crypto (USDC). Enterprise: invoicing and purchase orders through sales.
Prices are exclusive of applicable taxes. Where required, VAT/GST may be added on invoices.
No. Standard and Business have no minimums and no lock-in. You pay only for what you use.
The 8% Business platform fee applies to credit purchases. It is charged when you buy credits, not on individual API requests, and model token prices are the same as on every other plan.
No. Upgrade from the settings of the account or organization you want on Business. There is no contract, no minimum spend, and no sales conversation. You can downgrade 30 days after the upgrade, from the same place.
Usage and Rate Limits
OpenRouter sets no plan-based rate limit on paid models. A limit you hit there normally comes from the provider, and fallback routing retries other providers automatically; only very high burst traffic is rejected by OpenRouter's own DDoS protection with a 429. Free models are capped at 20 requests per minute and 50 per day, rising to 1,000 per day once your account has bought at least $10 of credits. Failed attempts count toward that daily cap, and a negative balance blocks free models until you add credits. Details are in the rate limits documentation.
Yes. Workspaces give each environment its own keys, limits and activity: 5 workspaces on Free and Standard, 1,000 on Business. Within a workspace, each API key can carry its own credit cap.
No plan-based ones. On Standard, Business and Enterprise, limits on paid models come from the provider, not from your plan; only OpenRouter's DDoS protection can reject very high burst traffic. Free models carry the caps in the answer above.
Routing and Latency
Yes. In-region routing is included on Business and Enterprise plans. Send requests to eu.openrouter.ai to keep inference with providers in the EU, or to us.openrouter.ai to keep it in the US. Upgrade to Business from your settings; for Enterprise, contact sales.
Routing improves reliability; latency varies by model, provider and region. For consistent latency, pin a specific model and provider.
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.
Yes. Choose an explicit model ID/version to avoid unexpected changes. You can also switch models without changing your integration.
Privacy and Security
No. We do not train on your data. Provider-side retention can be disabled for the account or per request, and Zero Data Retention routing is available on every plan.
SSO (SAML) and SCIM are available on Enterprise plans; contact sales to enable them. Business and Enterprise plans also include Workload Identity Federation, which lets your services call OpenRouter with tokens from your own identity provider instead of long-lived API keys.
Models and Features
Our API is OpenAI‑compatible. Update the base URL and model names; see Quickstart.
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
Routing/fallback can automatically try alternative models, and an attempt that errors is not charged for its model tokens under Zero Completion Insurance.
Visit the status page for real‑time uptime and incident history.
Support
Enterprise accounts get a support SLA with committed response times, a dedicated Slack channel with the OpenRouter team, a customer success manager who owns the account, and a forward-deployed engineer for integration, routing and rollout work. Standard and Business use email support, and every plan can use the community Discord.
Ready to get started?
Join thousands of developers building with OpenRouter