Open-model account and access

How do I create an account?

Sign up at Create an account with one of the two supported social sign-in methods, or email and a password of at least 8 characters; the form lists the choices. No card required, and new accounts start with $1 in credit for testing the open-models service. Confirmation and password-reset links work in any browser, and an expired link says so with a resend option.

What is a workspace?

A workspace, shown as your account in the dashboard, groups your API keys, members, and credits, with one balance for the open models API usage. Every account starts as Personal.

Is there a business account?

Yes. Only the owner can switch Account type to Business at Settings > Account and enter the company name in Account name. The switch is reversible.

• Invoices carry the company name, billing address and tax ID you set at checkout or with Manage billing details on Settings > Billing. Settings > Account shows them read-only, and its Manage billing details opens the billing portal.
• Audit logs are available on Business accounts and Enterprise plans at Settings > Security. The owner can review every recorded access, key, member and billing event from the moment the account becomes Business, and nothing before it.

Who receives billing notices?

The owner can set one email address as the Billing contact at Settings > Account. Purchase receipts, balance and spend alerts, payment issues, plan changes and account holds go there, with the owner copied. Clear it to send them to the owner alone.

A billing contact gets no account access, sign-in or permissions. Security and account emails, such as sign-in links and API key expiry warnings, always go to the owner, never to the billing contact. The invoice for a purchase follows the payment account; this setting cannot move it.

Do partners get different prices?

Yes. The open-models service arranges prices per account and per model. You see your agreed prices while signed in. They apply automatically when you call a covered model with your account's API key. The response's usage.cost reflects that price.

Partner pricing at Settings > Billing lists each covered model with Your price beside List price. The section is hidden for accounts without arranged prices. GET /v1/models returns your account's prices when called with its API key.

Partner pricing is not self-serve. Contact us.

How do I invite a teammate?

Open Settings > Members and enter their email. They receive an email invite, valid for 14 days, whether or not the address already has an open-models account. They join the inviting account when they select Accept invite in that email and then Join, or when they sign in or sign up with that address. Until then, the owner sees a Pending row and can select Revoke on the same page. There are no per-seat fees.

Can I delete my account?

Yes, self-serve, at Settings > Account. Deletion is immediate and permanent, and ends a coding plan at once, with no refund of the current month.

• The dialog lists what will be removed, including any remaining credit balance, which is forfeited, and any blockers.
• Confirm by typing the confirmation phrase. Password accounts re-enter their password. OAuth-only accounts need a sign-in within the last 10 minutes, or an email verification code.
• Deletion waits while an automatic recharge is settling: try again in a few minutes, and contact support if it keeps waiting. Starting deletion pauses new automatic recharges until you finish, or until you save your auto recharge settings again, which resumes them for every workspace where it is enabled.

How do I export my data?

For a workspace data export, contact support. We can prepare a signed export without exposing API keys.

Which emails does the open-models service send?

Two switches at Settings > Notifications, per user, applied immediately:

• Product notifications (on by default): low or depleted credits, spend limit and coding plan limit alerts.
• Daily billing digest (off by default): the last day's settled, held and refunded amounts for the accounts you own.

Security and account emails, such as sign-in and password links and API key expiry warnings, are always sent to the owner.

What happens now that coding plans are retired?

Coding plans retired for new customers on 2026-11-03. You cannot buy, keep, resume, upgrade or downgrade a plan, and none renews. Existing holders keep service until their own paid period ends. Eligible workspaces of the open-models service receive never-expiring credits worth one month of the plan now, as soon as the plan's end is scheduled. The credits are already in your wallet when the plan ends, so your keys keep working on credits. Workspaces with a live plan at retirement receive about 20% extra on top-ups for 12 months (for example, $29 buys $35 of credit), unless partner pricing applies.

A plan qualifies unless its payment was refunded, reversed or disputed. Plans that ended before 2026-11-03 at 00:00 UTC receive no retirement credit.

You can ask support for a full refund of your latest monthly plan payment instead. Your plan then ends at once, and any unspent retirement credit is removed. A payment dispute removes it too.

An owner can view the end date and change credits after limits at Settings > Coding plan.

How is usage counted?

At our standard per-token prices, with cached input at the cached price. Plan usage is not a credit deposit and does not roll over. Monthly usage is approximate: months hold different numbers of weekly resets.

When do the limits reset?

Your 5-hour window starts with your first plan request, and the next request after it ends starts a new one. The weekly limit resets on a fixed schedule from activation. The plan pays while both have room.

What happens at a limit?

Credits pay if you chose Keep full speed on credits (with a cap, or no limit), then free Standby serves chat. Until the plan ends, an owner can change this setting at Settings > Coding plan. If neither can serve a request, it stops with the reason, reset time and next step.

What is Standby?

Free, slower service when we are busy, up to a daily amount. Standby covers chat only. It refills at midnight UTC, may be reduced or paused, and is off while a plan payment is due or processing, or credits are owed.

What does my plan cover?

Chat (chat completions, messages and responses), plus embeddings and rerank whenever those models are available, from every workspace key except keys marked Credits only. Images and audio always stay pay as you go.

Can my team share the plan?

Yes, until it ends, it is shared by the workspace, not per member. Only an owner can change credits after limits or connect a terminal with runinfra login. Members create their own API keys at Settings > API keys and point their agents at them.

Can I keep an app on credits?

Yes. An owner marks its key Credits only at Settings > API keys. It always uses credits and keeps its wallet and key limits.

What can I count on?

Requests that fail before returning output never use your plan. Client cancellations count usage, as in pay as you go. Metering changes come with written notice, and promotional rates are labeled temporary.

What if a payment fails or is disputed?

If a renewal failed before retirement, your plan can keep serving for up to 48 hours, or 7 days if it has had a paid renewal. Select Pay overdue amount at Settings > Coding plan. That failed payment can still be collected automatically until your period ends; contact support to cancel it. A disputed payment pauses the plan, ends it at the period end and removes any unspent retirement credit. A dispute decided for the cardholder ends it at once. A bank inquiry alone changes nothing.

Can I cancel?

Your plan already ends at its paid period end and won't renew. There is nothing to cancel for a normal plan. While a payment dispute is open, an owner can select Cancel now at Settings > Coding plan to end it at once. A cancellation cannot be undone. Deleting your account ends it at once, with no refund of the current month. Existing credits keep their expiry dates. Retirement credits never expire.

Can a coding plan payment be refunded?

You can ask support for a full refund of your latest monthly plan payment instead. Your plan then ends at once, and any unspent retirement credit is removed. A payment dispute removes it too. A bank inquiry alone changes nothing. A coding plan that never starts serving is refunded in full. A renewal or an upgrade charged after you delete your account is refunded too. See Terms of Service, section 7.

What rate limits apply to my account?

Three limits govern your open models API requests:

1. Requests per minute, per API key. The default is 10,000 before your first credit purchase and 50,000 after it. Enterprise plans default to 200,000. Provider partners have a provider-grade rate. Each key follows your workspace default. A key that already has a custom limit keeps it, clamped to the workspace maximum.
2. Tokens per minute, per model. Each model has its own budget for your account. Credit purchases and net coding plan payments contribute to that budget. A model keeps its own default if it is higher than the tier's minimum.
3. Concurrent requests, per model, on pay as you go. Before your first credit purchase, your share is a quarter of the model's capacity while the model is busy, and up to half of it while it has spare capacity. Your first credit purchase raises your share of a busy model. Later purchases do not change it. Read the current allowance from the model list.

The Rate limits section at Settings > API keys shows all three limits and your token tier. The per-model table and the token tiers are under All limits and tiers. Each model's published concurrency allowance is available on GET /v1/models as max_concurrent_requests_per_api_key.

How do I raise my limits?

Add credit at Settings > Billing. Your first credit purchase, from $5, unlocks paid standing with a higher request rate. Your token budget follows lifetime purchases, not your remaining balance:

A top-up raises your token tier as soon as payment settles. Your earned tier never goes down. Promotional credit does not count. Current Pro and Team workspaces keep their earned token allowance after their coding plan ends, including any higher existing limit. Read the current limit from max_tokens_per_minute_per_workspace in GET /v1/models. See Coding plans and Standby.

Enterprise is arranged with the open-models service, not unlocked by a purchase. It has no practical token limit, a 200,000 requests per minute default per key, and the same concurrency share as the top paid tier. Contact us.

Which key should I create?

Use a workspace API key for hosted models. Select the model with the model field in the request body. See Authentication.

Can I rotate or revoke a key?

Yes. Open the key's row menu at Settings > API keys and choose Rotate or Revoke. A revoked key is refused on its next request. Requests already in flight can finish.

Can I copy a key again?

Yes, with the copy button on the key's row at Settings > API keys. Only the member who created the key and the workspace owner can copy it, and every copy is recorded in the audit log. A key created before copying was available was stored only as a one-way digest and cannot be shown again: create a new key, or rotate it from its row menu.

Do keys expire?

Only if you check Set an expiration date under Limits when you create the key: 30, 60 or 90 days, or 1 year. After a rotation, the previous key keeps working for up to 24 hours, as described in Authentication. An expired key returns 401.

Is SSO supported?

Sign-in today is email and password, or either of the two OAuth sign-in methods shown on the sign-in page. SAML or OIDC single sign-on is not available on the open-models service today. It is an Enterprise conversation. Contact sales.

Do you train on my data?

No. The open-models service never uses request and response content for training. Prompt text is not stored at all: what the service keeps per request is usage metadata for billing, and a response body only inside an idempotent replay window you open yourself. The full account, including what exists only while a request is in flight, is in Data retention.

Is traffic encrypted?

Yes. TLS 1.2 or above everywhere. All traffic to the open-models API is over HTTPS.

What compliance and contract options do you offer?

The open-models service is not offered for protected health information today. HIPAA and a BAA are not available. GDPR commitments, signed data processing terms, region-locked deployments, and VPC or private-link networking are contract conversations rather than self-serve settings. Contact sales.