Skip to content

RedDB navigation

RedDB Models

Choose the model. Keep your application.

A planned OpenAI-compatible model API for applications, the database and agents.

Planned service. No self-service deployment yet; we onboard early users by email.

Proposed flow Planned
  1. Your application 01
  2. Model API 02
  3. Chosen model 03
Use a familiar API while keeping model choice and spending explicit.

What is planned

Built around your workload.

Teams bringing model inference into their apps and agents.

  • 01

    A familiar integration

    An OpenAI-compatible endpoint for supported models, with an explicit catalog at launch.

  • 02

    Models for your workload

    Chat and embeddings for application features, ASK and agent workflows.

  • 03

    Consumption you can follow

    Usage attribution and spending controls are part of the managed-service plan.

How it works

One OpenAI-compatible endpoint and one key for the models we carry — usable from your application, from RedDB itself and from our agents.

How it is planned to work

  • 01

    One endpoint, one key

    Call chat and embedding models through a familiar OpenAI-compatible API.

  • 02

    Plugged into RedDB

    A database without its own provider can use RedDB Models for ASK and embeddings. Bringing your own key stays first-class.

  • 03

    One balance across products

    Redcode, Agent Memory and the coding agents are planned to draw on the same token balance.

You would pay for

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

Not promised yet

  • The supported model catalog and rates will be published at launch.
  • Not available yet; the database works with your own provider keys today.

Source: planning record, as of 2026-09-24.

Related services

  • AI services

    Agent Memory →

    Persistent memory for agents, built on RedDB and planned as a managed service.

  • AI services

    AI Storage →

    Planned storage and sharing for plans, designs, reports and other agent artifacts.

  • Agent execution

    Agent Hosting →

    Planned managed hosting for Hermes Agent, OpenClaw and Paperclip, with persistent customer environments.

Pricing

Plan the workload before the bill.

Model consumption is planned around input, output and applicable cache tokens. Published rates and supported models will be confirmed before launch.

Early access

Help shape RedDB Models.

Tell us what you want to run, which models or runtimes you use, and what you need to keep. We will discuss fit and availability before any deployment.