For developers building with AI memory.
Everything in Free, plus
- Auto top-up with configurable purchase limits
- 3 team seats, unlimited end users
- Priority support
Every plan comes with a monthly balance of credits. Calls draw from it at the same rates whichever plan you are on, and only unique content is ever billed.

Tried almost everything — structured memory files, qmd etc. The only thing that works reliably is supermemory.
Not facing any memory issues after setting it up.
Harshil MathurFounder, Razorpay100B+tokens a month187msmedian recall
For developers building with AI memory.
Everything in Free, plus
For developers who need more headroom than Pro.
Everything in Pro, plus
For teams and production workloads.
Everything in Max, plus
Enterprise
For organizations with committed spend, custom deployments and their own security requirements. Unlimited usage, metered your way.
Billed in SM tokens, the unique tokens we actually ingest. Repeats and unchanged content are free, and the rates are the same on every plan.
Plain text$5/ 1M SM tokens
Rich content$10/ 1M SM tokens
Text$1/ 1M SM tokens
Rich: images, PDFs, audio, video$2/ 1M SM tokens
Per query$5/ 1M queries
Per operation$100/ 1M operations
Each plan's monthly credits, spent on one meter alone. Real usage mixes them, and the rates are the same on every plan.
| Plan | Credits a month | Memory, plain text | SuperRAG, text | Searches |
|---|---|---|---|---|
| Free | $5 | 1M tokens | 5M tokens | 1M |
| Pro | $20 | 4M tokens | 20M tokens | 4M |
| Max | $130 | 26M tokens | 130M tokens | 26M |
| Scale | $600 | 120M tokens | 600M tokens | 120M |
For example, an app with 1,000 users who each add 20,000 tokens of conversation to memory and run 200 searches in a month uses about $100 of memory ingestion and $1 of search: about $101 at list rates, inside the $130 of credits the Max plan includes.