Trio-Flash Upcoming Public Preview

Give your agent
a next move.

A decision API for the moments that move your world forward. Give it a task, the current state, and a set of choices.

Playground opening soonView API example

$0.042 / million input tokens · Output free · $5 to start

Public Preview is being prepared. The playground and API keys open after live service validation.

01 / A restaurant, right nowInput example

◎Kitchen2 orders ready

◷Entrance1 guest waiting

1 staff member available

Orders ready

What should the available staff member do next?

01Deliver the ready orders
02Seat the waiting guest
03Wait for more information

Illustrative inputs only. Change the state to explore a request; no model has been called here.

{
  "model": "trio-flash-preview",
  "task": "Choose the next task for the available staff member.",
  "state": {
    "ready_orders": 2,
    "waiting_guests": 1,
    "payment_requests": 0,
    "available_staff": 1
  },
  "choices": [
    {
      "id": "serve_orders",
      "description": "Deliver the ready orders"
    },
    {
      "id": "seat_guest",
      "description": "Seat the waiting guest"
    },
    {
      "id": "wait",
      "description": "Wait for more information"
    }
  ]
}

Model playground opening shortly

01 / Your world

Bring the current state.

A game turn, a queue of requests, or a scene described in text or JSON. You define the task.

02 / Your choices

Define the next moves.

Supply 2–8 choices with your own IDs and descriptions. Keep the actions meaningful to your application.

03 / Your application

Make the decision useful.

Receive a choice and probabilities. Your code decides when to act, ask for review, or wait.

One request. Your use case.

Small decisions.
Room to build.

Start with a task you can check: selecting a game action, assigning the next job, or routing a request. When the playground opens, try your own states and choices.

The API returns a choice ID, probabilities, a decision status, and usage. Review uncertain choices before turning them into actions.

This is a request example, not a measured result. When the playground opens, the platform will show the current input limit and availability.

The model playground is opening shortly.

curl https://platform.machinefi.com/api/flash/v1/decisions \
  -H "Authorization: Bearer $TRIO_FLASH_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "trio-flash-preview",
  "task": "Choose the next task for the available staff member.",
  "state": {
    "ready_orders": 2,
    "waiting_guests": 1,
    "payment_requests": 0,
    "available_staff": 1
  },
  "choices": [
    {
      "id": "serve_orders",
      "description": "Deliver the ready orders"
    },
    {
      "id": "seat_guest",
      "description": "Seat the waiting guest"
    },
    {
      "id": "wait",
      "description": "Wait for more information"
    }
  ]
}'

Simple, pay as you go

$0.042

per million billed input tokens · output free

$5minimum prepaid balance

No subscriptionpay for successful judgments

A 400-token request costs $0.0000168. A 1,000-token request costs $0.000042. Actual cost depends on your task, state, and choices.

Completed judgments, including review or abstain, are billed. Failed requests and idempotent replays are not. Private template overhead is excluded. Preview pricing.

A first glimpse of Trio’s
decision intelligence.

Trio-Flash brings the decision side of Trio to developers through a hosted API. Start with a small, testable problem. See what it can help you build.

Preview capabilities vary by task. Test on your own examples before relying on a decision. Video and sensor understanding are not inputs to this API.

Give your agenta next move.