FrontierRLStar for robots

FrontierRL Star · robotics

Robotics doesn’t have a reasoning problem… It has a throughput problem.

Robots need an optic nerve; a model that can look at a live feed and say what is happening, fast enough that the answer still applies by the time the joint moves.

Sensor

Camera, depth, audio,whatever the device already has.

Star as the optic nerve

Reads the scene, tracks what changed, decides the next action in context.

Controller

Your stack. Star returns intent and (with training) motor commands.

Our model Star reads data at thousands of tokens per second on a single GPU, understands long moving scenes better than frontier options, and costs $0.40 per 1 million output tokens. Fast enough for the control loop, cheap enough to leave running.

Stress tested through video games.

FrontierRL loves reinforcement learning. We use video games as the ultimate simulation for fast-paced, real-time work. Too slow? Too late, kicked off the island. We’re proving Star can take in a live visual feed and correct the action coming out, continuously, with no task-specific scripting underneath.

Can your LLM do this?

Reflex loop

Real time, no scripting

See full matches at 60fps. Star reads the screen and reacts faster than frame budget, with nothing game-specific hardcoded.

Watch the full demo ›
Fleet

Six agents, one objective

Over time Star agents worked together and organically learned more efficient gameplay strategies. Save latency by treating multiple input streams as such.

Watch the full demo ›
Hardware

No API needed.

Star uses Autodesk Fusion through a real GUI. No API required. She’s able to use web, emulator controllers, keyboard, and mouse. All we gave her was a 2D schematic.

More demos ›

Fast enough for the loop.

Decoding throughput, measured as tokens per second. This is the slowest Star will ever be. Further training and better GPUs easily double this number.

Cheap enough to leave running.

A robot does not get to sample the world occasionally. Perception runs the entire time the device is powered on, so price per token is not a footnote, it is the line item that decides whether this is a demo or a fleet. See how far $100 gets you compared to frontier options.

Without compromising on quality.

See how Star compares to other frontier options. We’re offering frontier inference, inhuman speed, for bottom of the barrel prices.

EvalFrontierRL StarClaude Fable 5Claude Fable 5 (Xhigh)Claude Opus 4.8Gemini 3 ProGemini 3.1 ProGPT‑5GPT‑5.5GPT‑5.6 Sol (High)GPT‑5.6 Sol (Max)Source for other model's metrics
Video-MME v283%77%66.1%44.7%67%69%In-house tested by FrontierRL
IFEval97.97%92.1%96.64%In-house tested by FrontierRL
OSWorld Verified85.36%85%83.4%76.2%78.7%anthropic.com/claude/mythos

Full comparison across every eval we run is available on the benchmarks page.

Building something that moves?

Email [email protected] and tell us what your device has to see; we’ll tell you straight whether Star can be your optic nerve.

Give it eyes