Open-model pricing and credits
Updated
- Pay-as-you-go credits
- What a token costs
- Rate limits
- Adding funds
- Spending controls
- At zero balance
- Details you may need
The open-models service has one balance per workspace. One credit is one US dollar. Add credits when you need them and pay as you go.
| Connection | Value |
|---|---|
| API base | https://api.runinfra.ai/v1 |
| Workspace key | rp_... |
| Process variable | RUNINFRA_GATEWAY_KEY |
| Billing | The existing funding rules of your open-model account. |
Coding plans retired for new customers on 2026-11-03; existing holders are served until their own paid period ends. See Coding plan for retirement, your remaining limits, credits and refunds.
Pay-as-you-go credits
| Field | Value |
|---|---|
| What a credit is worth | $1, everywhere |
| Free on signup | $1, once per account, never expires |
| Top-up credit | Lasts one year from purchase |
| Minimum top-up | $5 |
| Maximum per top-up | $1,000,000 |
| Where you add funds | Settings > Billing |
| How you pay | Card, or USDC for one-time top-ups up to $10,000 |
| Seats | No per-seat fees, on any workspace |
What a token costs
Priced per model. When rates are published, the model's page in the Model Library lists input, cached input and output rates per million tokens; without a separate cached rate, cached input bills at the input rate and the page says so.
No minimum spend: every account can call the open models API.
Partner pricing
- The open-models service arranges prices per account and per model. It is not self-serve: contact us.
- Partner pricing at Settings > Billing lists each covered model with your price beside the list price, and appears only when prices are arranged. You see your agreed prices while signed in.
- They apply automatically when you call a covered model with your account's API key.
GET /v1/modelsreturns your prices for that key, and the response'susage.costreflects them.
Rate limits
Three limits govern the open models API requests for your account:
- 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.
- Tokens per minute, per model. Credit purchases and net coding plan payments contribute to your token tier. Each model keeps its own default if it is higher than the tier's minimum.
- 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.
See Rate limits at Settings > API keys for your current limits and 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_.
The credit milestones below describe pay-as-you-go standing. 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_ in GET /v1/models. Standby has separate capacity limits until the plan ends. See Rate limits.
Raise your token tier
| Tier | Lifetime credit purchases | Tokens per minute, per model |
|---|---|---|
| Model defaults | Less than $50 | Each model's own default |
| Raised model allowance | $50 to less than $200 | Read the current allowance from the model list |
| No practical limit | $200 or more | No practical limit |
| Enterprise | By arrangement | No practical limit |
A top-up raises your token tier as soon as payment settles. Your tier never goes down, even as you spend your balance. Promotional credit does not count. Your first credit purchase, from $5, unlocks paid standing with a higher request rate, before you reach a higher token tier.
Adding funds
- One-time top-ups from $5 to $1,000,000 at Settings > Billing, in any whole-dollar amount. Pay by card, or with USDC (a US dollar stablecoin) on one-time top-ups up to $10,000 that don't save a card. Secure checkout collects your payment details and billing address, offers an optional VAT or tax ID field for business purchases, and shows the exact charge before you confirm.
- Auto recharge is off until you turn it on at Settings > Billing. When your balance falls below your threshold, the open-models service charges the saved card, up to a monthly ceiling you set; with no saved card, turning it on first runs one top-up through checkout that saves it.
| Auto recharge setting | Starting value | Range |
|---|---|---|
| Threshold | $10 | $1 to $1,000,000 |
| Recharge amount | $50 | $10 to $1,000,000 |
| Monthly ceiling | $500 | $10 to $10,000,000 |
The recharge amount must be at least the threshold.
A card decline that requires your action pauses auto recharge and flags it for attention. Temporary declines can retry after a six-hour backoff. Turning auto recharge off stops new attempts, but an attempt already in progress may still complete. Credit is added when the payment confirms, never before, and an automatic recharge counts toward lifetime purchases exactly like a manual top-up.
Credit checkout does not take promotion codes. A refresh, a back button or a bank verification return resumes the same payment, so a reload never charges you twice.
Invoices and billing contact
- The owner selects Manage billing details at the top of Settings > Billing to open the billing portal, where you edit the company name, billing address and tax IDs on your invoices, manage saved cards, and browse every finalized invoice.
- The owner sets one 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.
- Every purchase issues an invoice carrying your checkout details. It follows the payment account; the billing contact cannot move it.
Spending controls
Credits fund pay-as-you-go work. A coding plan's Cap per billing period limits only credits spent after a plan limit, not other pay-as-you-go work.
Set an optional monthly spending limit per API key at Settings > API keys. Pay-as-you-go requests on that key return 402 spend_limit_reached once its settled spend reaches the limit. See Authentication.
To bound automatic charges, use the auto recharge monthly ceiling.
At zero balance
A serving coding plan can cover eligible requests at zero credit balance. These credit rules apply to pay-as-you-go work:
- Calls to the open models API return
402 Payment Requiredand are not billed. See Errors. - If a settlement drives the balance below zero, the workspace pauses new billable work. Your next top-up offsets the negative amount first.
Details you may need
When do funds expire?
Balance from a top-up lasts one year from purchase, manual and automatic alike. The $1 signup grant never expires. Whatever expires soonest is spent first, so a top-up is never stranded behind funds that expire later.
I still have a legacy credit subscription
A small number of workspaces hold one from before credit subscriptions were retired, and nothing about those changes: it keeps granting its monthly balance, which expires at the end of each billing period. Its invoices are listed under Invoices on Settings > Billing, alongside the invoices credit purchases now produce.
New legacy credit subscriptions cannot be started. Coding plans are a separate product and do not grant a monthly credit balance. To move a legacy workspace onto credits, contact support; that switch is not self-serve today.
What about Enterprise?
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.