Latency
Start free. Scale without limits. No contracts, cancel anytime.
Real-time memory across all tiers.
Your tier determines scale, not speed.
Each extracted fact, preference, or relationship from a conversation turn is one memory. A single conversation turn typically produces 1–5 memories.
Yes. Upgrade instantly, downgrade at end of billing period. No contracts, cancel anytime.
Extract calls will return a 429 error. Recall continues to work. Upgrade to a higher plan for more capacity.
Pro gives you 100K memories with 25 agents at $29/mo — great for production apps. Scale adds Graph Memory, 1M memories, unlimited agents, priority support with SLA, and advanced cognitive features at $89/mo (64% less than Mem0's comparable tier).
Yes! Save 20% with annual billing. Pro drops to ~$23/mo ($278/yr) and Scale to ~$71/mo ($854/yr). Use the billing toggle above to see annual prices.
Graph Memory maps relationships between memories — people, concepts, events — with entity extraction, sentiment analysis, and confidence scoring. Your agent doesn't just recall facts — it understands context, emotional weight, and how reliable each memory is. Available on Scale and Enterprise plans.
Negative Recall lets your agent know what it should not say or do — corrected facts, retracted preferences, deprecated instructions. Available on all plans.