DreamerOS

Plans

You do not pay until the free plan stops being enough.

DreamerOS adds account memory, route-specific checks, and receipt attempts around the AI work your plan can use. Start free, then move up for more engine choice, memory, checks, or team controls.

The diagram shows the point where routed work stops before it can cost more. The five plan cards below show the engine count, memory, and receipt limit for each choice. Free stays free; the next step up is $14.00/mo.

Try it free. No card, ever.
Plan ceilings that stop routed work before it costs more
The plan boundary is visible before routed work can cost more

Light

Light: Free

Light costs nothing, and it is not a trial. Ask a question and the router selects one of all five engines. The normal path shows which pre-checks ran and attempts a receipt. It holds up to 100 things about you and lets you collect 25 a day, no card, no clock running out. The day the daily receipt cap gets in your way, Solo is worth the jump: one engine you pick yourself, cross-session memory, post-check access, and no daily receipt cap.

  • Light engines: all five engines
  • Memory: remembers 100 things about you
  • Receipts: 25 a day
  • Speed: 10 requests an hour
  • In your own tools: yes, an MCP key is included
How this works
five customer engine families available, one routed per answer pre-checks on the normal path; post-check access begins at Solo current-session continuity; cross-session memory begins at Solo receipt minting capped at 25 a day
Plan ceilings that stop routed work before it costs more
The plan boundary is visible before routed work can cost more

Solo

Solo: $14.00/mo

Solo trades Light's five available engine families for one you choose and keep: ChatGPT, Claude, Gemini, Grok or Perplexity. The normal path adds pre-checks and post-checks. Solo holds up to 1,000 things instead of Light's 100, and never caps how many receipts you mint in a day. That is the jump that matters most: cross-session memory and post-check status become available.

  • Solo engines: 1 connected engine: pick from ChatGPT, Claude, Gemini, Grok, Perplexity
  • Memory: remembers 1,000 things about you
  • Receipts: no daily cap
  • Speed: 50 requests an hour
  • In your own tools: yes, an MCP key is included

Available on higher tiers: automations, top media powers, three transcribers on your audio, deep claim checks, the Direction Set Workshop or a live ops feed.

How this works
one connected engine family, your pick pre-check and post-check on the normal route no daily receipt cap session handoff for supported app and connected-client paths
Plan ceilings that stop routed work before it costs more
The plan boundary is visible before routed work can cost more

Duo

Duo: $24.99/mo

Duo gives you two chosen engine families instead of one. Both can use account memory on supported paths, and the router selects between them for each question. Automatic memory parity in every client remains In Beta 2.0. Duo keeps the same 1,000 memories and no daily cap as Solo, twice the coverage, one shared record. The honest jump: a second engine you pick yourself, checking the first one's work, at no extra memory cost.

  • Duo engines: 2 connected engines: pick from ChatGPT, Claude, Gemini, Grok, Perplexity
  • Memory: remembers 1,000 things about you
  • Receipts: no daily cap
  • Speed: 50 requests an hour
  • In your own tools: yes, an MCP key is included

Available on higher tiers: automations, top media powers, three transcribers on your audio, deep claim checks, the Direction Set Workshop or a live ops feed.

How this works
two connected engines, your pick, one shared memory the system chooses which engine answers each turn same memory ceiling and speed as Solo session handoff in the app and both connected engines
Plan ceilings that stop routed work before it costs more
The plan boundary is visible before routed work can cost more

Pro

Pro: $39.99/mo

Pro makes all five engines available and lets the router select one for what you asked unless a named route sends the request to several engines. Pro memory jumps to 10,000 and supported connected actions can prepare or run work under their own approval rules. File, image and audio paths show whether they were read or refused. This is the strongest individual plan before team controls.

  • Pro engines: all five engines
  • Memory: remembers 10,000 things about you
  • Receipts: no daily cap
  • Speed: 100 requests an hour
  • In your own tools: yes, an MCP key is included

Available on higher tiers: top media powers or a live ops feed.

In Beta 2.0: One more connection is not included in any plan. The plan item exists, but customers cannot buy or request it in the app.

Pro can grow with the listed add-ons. Elite-only team management, role-based access, shared outputs, and priority support remain with Elite.

How this works
five customer engine families available; one selected unless a named route sends the request to several engines file, image and audio routes report whether input was read or refused connector actions follow the approval rule implemented by that route memory and rate both step up sharply from Duo
Plan ceilings that stop routed work before it costs more
The plan boundary is visible before routed work can cost more

Elite

Elite: $149.00/mo

Elite is a team plan carrying one price for everyone on it. The whole team shares one audit trail and one memory policy, so the work reads the same no matter who on the team asked it, with role based access on top. Elite memory climbs to 100,000 and requests to 500 an hour, past what one person alone will ever need, and your questions jump the line. The jump to Elite buys what a team needs and one person does not: a shared record, roles and priority support, on top of top media powers and a live ops feed.

  • Elite engines: all five engines
  • Memory: remembers 100,000 things about you
  • Receipts: no daily cap
  • Speed: 500 requests an hour
  • In your own tools: yes, an MCP key is included
How this works
one shared audit trail and one memory policy for the team role-based access and custom routing rules the largest memory and rate ceiling on the ladder priority support
Plan ceilings that stop routed work before it costs more
The plan boundary is visible before routed work can cost more

Compared to the alternatives

OpenRouter is a usage-priced model marketplace and routing layer. DreamerOS is a monthly account layer for intent, memory, selected checks, and receipts when minted. They can work together; they are not the same product.

ChatGPT Plus sells access to OpenAI's consumer product. DreamerOS Pro makes all five engines available through DreamerOS for $39.99/mo, with deeper verification and account memory. Compare current provider pricing separately because it can change.

A raw provider API key supplies model access. DreamerOS adds account memory, route-specific checks, and receipt attempts around supported paths. Automatic parity in every connected client remains In Beta 2.0.