Use the customer console
Find account metrics, keys, model testing, usage, and profile settings.
Read the dashboard
Dashboard shows account balance and reported request, token, and billed-spend metrics. The readiness indicator describes portal availability; it does not guarantee that every model has capacity.
Create and copy an API key
If key editing is unavailable, use an existing active key or contact support. Creating a key does not add account balance. The rolling 5-hour, 1-day and 7-day limits are spend limits in USD, not requests per minute.
- Sign in to the console with your account email and password. Complete the authenticator challenge if your account requires it.
- Open API Keys and choose Create API key. Give the key a name you will recognize in Usage.
- Choose an available group if you need a specific model route. Otherwise keep the default assignment.
- Set a USD quota and optional expiry or IP restrictions, then create the key. A blank or zero quota means unlimited key spend, subject to your account limits.
- Use Copy API key to copy the complete value. You can also reveal an existing key. Store it in a server-side environment variable.
Try a model in the playground
An administrator can optionally configure an identity name and knowledge cutoff for a model in Playground. A short instruction then guides its replies when asked; it does not change the underlying model or its training. These instruction tokens count toward normal usage. Unconfigured models receive no added identity instruction.
The playground supports text conversations without attachments. Sent messages and replies are saved to your account and available when you sign in on another device. Unsent drafts stay in this browser tab. A refresh stops a live response and restores saved partial text without resending. Changing the key or model preserves the conversation, and your next message uses the new selection. First text and duration describe your last request, not a provider-wide latency guarantee. A listed model can still reject a request if capacity, balance, quota, or access changes.
- When Playground is enabled, choose it in the website header. If you are signed out, sign in to continue directly to Playground.
- Select an active API key and an enabled model beneath the message input. Saved chats, New chat, and Status & rates are in the left panel. If no models appear, choose another key or ask an administrator to enable models in Playground settings.
- Check Model status for key access and request activity. Reported channel status comes from monitoring and does not guarantee availability for your selected key.
- Open View rates to check final customer prices when available. Normal usage charges still apply when a current quote is unavailable.
- Enter your message and choose Send, or press Enter. Use Shift + Enter for a new line. Stop cancels the response; work already processed may still be billed.
- Open Billed usage to inspect actual charged amounts. New chat starts a separate conversation. Use Your chats to move between saved conversations. Replies continue while you visit another chat or console page. Sent chats remain in your account after sign-out.
Other account pages
Subscriptions shows assigned plans, validity dates, usage and limits when enabled. Redeem applies a supported redemption code. Profile contains the account settings available to your user. Availability depends on your account capabilities; there is no global routing or fallback editor in this console.
Verify the answer and billed usage
- Check the returned assistant message. An error response is not a successful answer.
- Open Usage and select a date range that includes the request. Check the displayed timezone.
- Find the request by its model and key name. Review input/output and cache tokens, latency, and actual billed cost.
- If a request is interrupted or times out, check Usage before repeating it. A retry is a separate request and can incur another charge.