Pay for what you use.
Credits included on every plan.

Every plan comes with a monthly balance. Calls draw from it at the rates below, 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, Razorpay

100B+tokens a month<300msp95 recall

Plans

  1. Free

    $0

    Try the API with no commitment.

    $5 of credits included each month

    • All plugins: Claude Code, Cursor, Hermes and more
    • Full search and memory API
    • 1 team seat, unlimited end users
    • Email support
    Start free
  2. Pro

    $19/mo

    For developers building with AI memory.

    $20 of credits included each month · everything in Free, plus

    • Pay as you go (auto-top ups with spend limits)
    • 3 team seats, unlimited end users
    • Priority support
    Get Pro
  3. Most picked

    Max

    $100/mo

    For developers who need more headroom than Pro.

    $130 of credits included each month · everything in Pro, plus

    • 6× the credits of Pro
    • Gmail connector
    Get Max
  4. Scale

    $399/mo

    For teams and production workloads.

    $600 of credits included each month · everything in Max, plus

    • S3 and web crawler connectors
    • Unlimited team seats, per-tag access
    • Dedicated support
    • SOC 2 · HIPAA BAA · self-hosted option
    Get Scale
  5. Enterprise

    Custom

    Custom deployments with dedicated engineering.

    Unlimited usage · everything in Scale, plus

    • Custom metering and billing
    • Custom integrations and SSO
    • Forward-deployed engineer
    Talk to sales

Rate card

Billed in SM tokens: the unique tokens we actually ingest. Repeats and unchanged content are free.

MeterRatePer
MemoryA memory graph per user: profiles and fact hierarchies that agents learn from in real time. Powered by our own model.Plain text$0.0051K SM tokens
Rich content$0.0101K SM tokens
SuperRAGMultimodal extraction, contextual chunking and retrieval. No embeddings or vectors to manage. Also available as a filesystem. smfs.aiText$0.0011K SM tokens
Rich: images, PDFs, audio, video$0.0021K SM tokens
Search and traversalSemantic search and graph traversal across stored content, in one call. Sub-300ms p50, built for agent loops.Per query$0.0051K queries
OperationsRe-ranking, aggregation, query rewriting and other building blocks for richer queries.Per operation$0.101K operations

Enterprise

For organizations with committed spend, custom deployments and their own security requirements.

Security and compliance

  • Air-gapped self-hosting, you own the data, or a dedicated managed instance
  • SOC 2 · HIPAA · GDPR
  • Custom contracts and DPA
  • Enterprise MCP

Scale and performance

  • Unlimited usage on committed-spend pricing
  • Custom rate limits and throughput
  • Dedicated infrastructure

Support

  • Dedicated account manager
  • Forward-deployed engineer
  • 1:1 onboarding and integration
  • Uptime SLA
  • Priority Slack channel
Talk to sales

Startups and research

Qualifying early-stage startups and academic research teams get the Scale plan free for three months, its included usage and dedicated support with it. Ship the agent; we cover the context.

Apply

Questions

How does the credit balance work?
Every plan comes with a monthly dollar balance. Each API call, whether storing memories, searching or indexing, draws from that balance at the rates above. Top-ups add to it whenever you like.
What is an SM token?
SM tokens are the unique tokens Supermemory actually ingests and embeds. Repeats and unchanged content are not billed again, which for most workloads means a large discount on the raw token count.
What happens if I store the same content twice?
Nothing is billed. Supermemory deduplicates at the token level, so re-uploading a document, re-syncing a connector or pushing the same conversation history costs nothing the second time.
Do unused credits roll over?
Subscription credits reset monthly. Credits you buy as a top-up never expire; they stay in your balance until you use them.
What happens when I run out?
On Free, usage pauses until the next month's credits arrive; there is no pay as you go. On Pro, Max and Scale, usage beyond the included credits is pay as you go at the same rates: auto top-up refills the balance before it runs dry, and spend limits keep a runaway agent from surprising you.
Can I self-host?
Self-hosted deployments are available on Scale and Enterprise. Enterprise also supports fully air-gapped deployments, where LLM inference may be the only outbound call, or none at all.
Do you offer startup or research credits?
Yes. Qualifying early-stage startups and academic research teams get the Scale plan free for three months, including its included usage, plus dedicated support.