Billing & Credits

Memo uses credits to meter work that involves computation — generation, analysis, and agent chat. Saving, organizing, and browsing are always free. Every plan comes with monthly credits, and every model shows its price in credits before you run it. A paid plan gives 70 credits for each dollar of its monthly price: $50 a month is 3,500 credits. Every price is a whole number of credits.

​

Plans

Annual billing gets you two months free ($150 / $500 / $2,000 per year). Monthly plan credits reset at each billing cycle — unused monthly credits don’t carry over. The full per-model price list lives on memo.solutions/pricing.

​

Top-ups

Need more than your monthly allocation? Credit packs are one-time purchases that never expire. Because they never expire, a pack credit costs more than a plan credit: Open your avatar’s account menu, select the credits balance, and choose a pack, or go to Manage workspace → Billing.

​

What costs credits

• Image generation in Studio — from 2 credits per image (Krea 2 Turbo drafts and Muse Image edits); a standard image on the default model (GPT Image 2.6 Flare, Medium effort, at its standard 2K size) is 14 (7 at 1K; High effort is 17 at 2K). Cost varies by model, output size (1K/2K/4K), rendering effort or thinking level where supported, and on some models (GPT Image, Krea 3) the number of reference images
• Video generation in Studio and the Video tool — cost varies by model, duration, and resolution (a 5-second clip ranges from roughly 40 credits at 480p to 1,100+ at 4K, depending on the model)
• Image analysis — extracting color palette, composition, style (~1 credit)
• Agent chat — varies with the model, conversation length, attached context, and the number of AI calls needed to complete the work

Every generation shows its credit price before you run it. The one exception is a reference video on Seedance or Wan 3.0, whose length is added when you run (see below). Credit deductions are atomic, so the balance can never go below zero. Automatic image descriptions and background search indexing do not deduct extra credits. Your image can be ready to view before it becomes searchable; finishing or retrying that background work does not charge for another image.

​

Reference fees

Some video models charge for the references you attach. Memo charges what the model provider charges for your exact references, plus the usual margin. You never pay for a worst case you didn’t use.

• GPT Image 2.6 and GPT Image 2.5: every reference image you attach adds the provider’s input-image cost, about 2 credits each. The base price is the text-to-image price.
• GPT Image 2: every reference image adds 1 or 2 credits.
• MiniMax H3: the first 5 reference images are free, then a flat fee per extra image.
• MiniMax H3 Max: reference images are priced by shape. Four square images are free. Wider images count for more, so a 16:9 image counts as nearly two square ones. For a 5-second 768p clip, nine square references add 16 credits and nine widescreen references add 37.
• Seedance 2.0 and 2.5: a reference video is priced by its length. You pay for your clip’s length plus the reference video’s length, at 60% of the usual per-second rate. A short reference can make the clip cheaper than using none; a long one costs more. For a 5-second 720p Seedance 2.5 clip, that’s 355 credits with no reference video, 298 with a 2-second reference, and 426 with a 5-second one.
• Wan 3.0: reference images are free. A reference video is priced by its length at the usual per-second rate, added to your clip’s length. A 5-second 720p clip is 75 credits on its own and 135 with a 4-second reference video. Reference videos can total 15 seconds at most.
• Genjutsu and Genjutsu Object Swap: the clip is as long as your source video, so the price follows that video, per second and rounded up. A 4.2-second source is charged as 5 seconds. Sources longer than 30 seconds are trimmed to 30; shorter than 4 seconds are refused before anything is charged.

Memo measures your references when you press Generate, holds that exact amount, and charges it when the clip finishes. The account menu and avatar ring show credits available to spend, after pending holds. The menu lists held credits separately from credits used this month. It refreshes when a watched image or clip is accepted, finishes, or fails, without a page reload. When a hold becomes a charge, those credits are counted once; if the hold is released, they become available again. The price on the Generate button already includes image reference fees. With a reference video on Seedance or Wan 3.0, it notes that the video’s length is added when you run. If a reference file can’t be read, the run stops before anything is held or charged. Re-export it as MP4/MOV for video or JPG/PNG for images and try again. Sometimes the image or clip is ready before its credit charge finishes. While credits remain held, Memo checks your workspace balance every five seconds while the page is visible and online. It stops checking when all holds clear, and resumes when you return to the page or reconnect. A slow or failed balance check keeps the last confirmed amounts on screen; it does not assume that a charge or refund succeeded.

​

How chat credits are calculated

Memo uses the provider’s reported cost for each AI call when available, then applies Memo’s markup and rounds up to a whole credit. The current minimum is one credit per billable AI call. A single message or creative brief can need several calls; it does not have a fixed per-message price. Image and video generations have their own charges. During the beta, Studio chat is billed at what it costs Memo, with no markup: a typical turn is a few credits, so your credits stay for images and video.

​

The monthly chat budget

Each workspace has a monthly chat budget, 1,000 credits by default, counted on the calendar month. A line under the chat composer shows how much is left. When it is spent, the chat says so and waits for the first of the month; your credits are untouched, and images, videos, the canvas and connected agents keep working. The budget exists so nobody spends a whole wallet on conversation by accident. Ask support if your workspace needs a different budget. When the provider reuses previously processed instructions or brand context, the lower cost of that reused input flows through to your chat credits. Creating a cache can cost more on the first call, so savings depend on how much context is reused across later calls. If the provider doesn’t report a cost, Memo estimates it from usage and model rates. For supported Claude models, that estimate accounts for both cache reads and cache writes. These efficiencies run automatically while you work on your brief.

​

Checking your balance

• Account menu: The ring around your avatar shows credits available to spend. Open the menu for your available balance, credits used this month, and any credits held for pending generations. The bar under the balance is everything you can spend and empties as you use it, so a full bar means nothing spent yet. When you hold top-up credits it has two colours, named beneath it: the brand blue is your monthly plan allowance, the deep blue after it is top-up credit that never expires. Select the balance for usage details.
• Manage workspace → Billing: Current plan, seat usage, limits, and an upgrade button. During a beta window it also says how many days are left and that unused beta credits stay on your account.

“Credits refresh” is the monthly credit allowance date, separate from your subscription’s payment schedule. An overdue refresh shows “Credit refresh pending”; a missing date shows “Credit refresh date unavailable”. Check Manage plan for your payment schedule. Staff workspaces show Staff and recorded usage, without a renewal date or upgrade prompt. When credits are low, pre-action warnings appear before credit-consuming operations. When exhausted, a dedicated upgrade prompt.

​

Credits and the monthly generation count

Two separate meters guard every image or video. Credits pay for the work. A monthly generation count caps how many runs your plan allows: 20 a month on Free; higher plans allow more, and some have no cap (see your plan under Manage workspace → Billing). The count resets on the first of the month and is lifted by upgrading, not by buying credits. A run that fails on Memo’s or a supplier’s side returns its credits and does not use up a generation. A run refused for content policy keeps its charge and counts as one. During a beta window the count and the storage limit are at least the Pro plan’s (10 GB of storage), so a full beta balance is never stopped by the Free plan’s caps. The Free plan’s limits return the day the window closes; nothing you stored is deleted.

​

Rate limiting

The system enforces per-workspace rate limits to prevent runaway costs:

• Studio chat: 60 requests/hour on free, 300/hour on Pro
• Generation: Per-workspace quotas checked before every generation
• Analysis and other endpoints: Tier-based limits

Hit a rate limit and you’ll see a clear message. Wait for the window to reset, or upgrade for higher limits. During beta, every workspace has a 20 GB hard storage ceiling. Uploads above it are refused with a clear message, and so are new generations: a generation that would push the workspace past its storage limit is stopped before any credits are held. Deleting a brand asset hides it immediately; Memo keeps the underlying file for 30 days before it is removed for good, so a mistaken delete can be recovered by support during that window.

​

Per-project cost tracking

Every Studio project tracks its own credit consumption via usage logs. This gives you visibility into what each campaign costs — useful for agencies billing back to clients or teams tracking creative spend. Billing is handled through Stripe — checkout, customer portal, and receipts. Upgrade from Manage workspace → Billing.

​

Tips

• Saving inspirations is free. Build your library without spending credits.
• Analysis results are permanent. Run it once, see the results forever. No re-charge on revisit.
• The credit exhaustion modal shows your exact balance and what you need to continue. No guessing.