Skip to content

RedDB navigation

AI pricing

AI services have their own resource use.

ASK, embeddings and vector search are features of RedDB Database — see Database pricing for Cloud plans. Models, memory, storage and agent hosting are planned services with separate consumption; proposed rates are listed below and are not available to purchase.

RedDB Models Planned

You would pay for

  • Input, cached-input and output tokens, per model
  • Usage drawn from prepaid credit, with the balance as the spending cap

The supported model catalog and rates will be published at launch.

Agent Memory Planned

You would pay for

  • Memory tokens (extraction and embeddings)
  • Retained memory storage, per GB-month
  • Not metered: retrievals, agents, end users or seats

Rates are proposed and the service is planned. The API shape, retention controls and bring-your-own-key options are still being decided.

AI Storage Planned

You would pay for

  • Stored GB-month
  • Writes and reads
  • Not billed: egress, links, viewers or seats

Rates are proposed and the service is planned. Planned as a convenience inside our agents, not a standalone storage product.

Cost drivers

  • Persistent compute, disk and network
  • Tool sandbox time
  • Model consumption and backups

Rates are proposed and the service is planned. Idle suspension, GPUs and support for every channel are not promised.

Proposed rates

These services are planned. Proposed rates are not an offer to buy.

AI catalogue rates
ResourceUnitUSD
GLM-5.3-Flash input1M tokens$0.509574
GLM-5.3-Flash output1M tokens$1.698578
GLM-5.3-Flash cacheRead1M tokens$0.169858
text-embedding-3-small input1M tokens$0.064402
DeepSeek V4.1 Flash input1M tokens$0.475602
DeepSeek V4.1 Flash output1M tokens$1.426805
DeepSeek V4.1 Flash cacheRead1M tokens$0.014269
Memory tokens1M memory tokens$1.500
Memory storeGB-month$1.500
StoredGB-month$0.130
Writes1M writes$38.000
Reads1M reads$3.000

As of 2026-09-24. Prices API