Trio-Flash: Give your agent a next move
One world state. A few allowed moves. One inspectable answer. Trio-Flash is a bounded decision API with a clear launch target: smarter choices than Jev, slightly slower, at the same planned $0.042/M limited-preview input price.
It is also a first look at where we are taking Trio. Our longer-term work is about intelligence for physical operations. Trio-Flash brings one focused part of that idea to developers now: turn a task, a current state, and a short list of possible actions into a decision your software can inspect.
Start with a problem you can see
Our first demo is Trio Falling Blocks. Its current build has passed local end-to-end validation and remains behind the launch gate. For each falling piece, the program enumerates legal placements and gives the model a short list of candidates. Trio-Flash chooses one placement. The board then shows the consequence.
The demo is deliberately easy to audit. You can see the board state, the candidate moves, the probability assigned to each move, the chosen action, and the resulting board. Fixed seeds let us replay the same piece sequence across Trio-Flash runs. One model request controls one piece, so the connection between a decision and its result stays visible.
Falling Blocks is a compact test, not the destination. The same API shape can help a restaurant assign the next staff task, a factory schedule a job, a home agent choose among allowed actions, or a trading simulator select a move inside predefined limits. In every case, the application owns the state, the choices, the safety rules, and execution.
The target: smarter decisions at the same price
Jev set a useful bar for fast hosted decision models. Our launch target is simple: make better decisions on the same test items at the same listed input price, while accepting that Trio-Flash may take a little longer to answer. We are especially interested in whether its probabilities help an application know when to act and when to ask for review.
That is a target, not a result we are asking anyone to take on faith. Before this post is published, we will run both services on a frozen evaluation, record the paired decisions, and measure live latency on the launch hardware. We will publish the measured table and its date if the comparison survives that gate. Until then, there are no accuracy, latency, or parity numbers in this post.
A cloud API, built for experiments
Send a natural-language task, a text or JSON state, and two to eight choices with IDs your application understands. The response contains a selected choice, probabilities, a decision status, and usage. Your code can execute the choice, request human review, or wait for more information.
Trio-Flash will launch as a closed, hosted service. We are not releasing its weights, model size, training method, or internal implementation during the preview. We will show the parts developers need to evaluate it: the API contract, inputs and outputs, reproducible demos, measured latency, benchmark protocol, service limits, and billing behavior.
The planned limited-preview price is $0.042 per million billed input tokens, with free output and a $5minimum top-up. It is pay as you go, with no required subscription. This is a subsidized validation rate while we test real demand and infrastructure economics; it is not a claim of sustainable production margin, and pricing may change before general availability. The current rate card and service availability will always be shown in the Playground before a paid request.
What Trio-Flash does and does not do
Trio-Flash makes a bounded decision from the state and choices you provide. It does not watch a camera feed, operate a robot, move money, or run a business on its own. Those systems must observe the world, enforce their own constraints, and decide whether to execute a model choice.
The limited preview is for developers who want to test small, repeated decisions against outcomes they can measure. Bring a game, a simulator, or a real workflow with a safe review path. The useful feedback is concrete: where did the model help, where did it hesitate, and would you keep calling it?
Try your own next move
The playground and API keys will open after the live service, billing flow, and launch measurements pass validation. Until then, see the Trio-Flash product preview and the example API request.
Trio-Flash is not affiliated with or endorsed by Jev. Preview capabilities vary by task; evaluate decisions on your own examples before relying on them.