Simple, transparent
pricing

Input and output tokens are billed per model at posted rates.

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.

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.

No. When routing/fallback is enabled, you're billed only for the successful model run.

Yes. We support prepayment credits, volume discounts, annual commits, and invoicing/POs.

No. Pricing is per token regardless of streaming. You pay only for successful runs when routing/fallback is enabled.

Pay-as-you-go accepts credit/debit cards, crypto, and bank transfers. Enterprise supports invoicing and POs. Contact Sales for procurement options.

Prices are exclusive of applicable taxes. Where required, VAT/GST may be added on invoices.

No. Pay-as-you-go has no minimums and no lock-in. You pay only for what you use.

For free plan — Yes. 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. Enterprise plans have dedicated limits. 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.

Yes. Create separate API keys per environment with their own caps, alerts, and activity logs.

No, there are no platform-level rate limits for Pay-as-you-go or Enterprise users. Free users have rate limits.

Yes. Regional routing is available on Enterprise and Pay-as-you-go plans.

Routing improves reliability; latency may vary by model/provider/region. If you need consistent latency, pin a specific model and region.

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.

No. We do not train on your data. Provider-side retention can be disabled at the account level or per API call.

Yes. SSO (SAML) is available on Enterprise plans; contact us to enable it on your account.

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.

Routing/fallback can automatically try alternative models. You're billed only for the successful runs. Every request has Zero Completion Insurance.

Visit the status page for real-time uptime and incident history.