Models · ACT (action chunking transformer)

act/so101

checking availability…

A specific checkpoint, vineetr196/act_so101_pickplace_v1, for the SO-101 arm. It answers one observation with the next 100 actions. It is not a general-purpose controller; it does not read a task sentence.

Price

per call: $0.01 · 100 tokens
per action: $0.0001
billed: every returned action, whether or not your robot plays it

What you send

observation.state [6]: shoulder_pan, shoulder_lift, elbow_flex, wrist_flex, wrist_roll, gripper · normalized: arm -100..100, gripper 0..100
observation.images.top [480, 640, 3]: top camera, RGB uint8 (JPEG on the wire)
observation.images.wrist [480, 640, 3]: wrist camera, RGB uint8 (JPEG on the wire)
task text: ignored by this policy

What comes back

100 actions × 6 joints, to be played at 30 Hz — 3.33 s of motion per call.

Units before motion.Values are LeRobot normalized (arm -100..100, gripper 0..100), not degrees. The semantics label depends on where you read it — the model catalog still answers so101-degrees-gripper-percent-v1, a lease and the wire answer the corrected label — and the data is normalized either way, so never branch on it (units, explained). LeRobot’s so101_follower defaults to degrees: run it with --robot.use_degrees=false. What the arm does if the connection drops.

Measured

policy: 19–67 ms
on the runner: 35–98 ms
client round trip: 59–157 ms

From a recorded probe on 2026-10-25 05:36Z. The round trip includes that client’s network; yours will differ. What each number measures.

Try it

One billed call with synthetic inputs ($0.01). No robot moves.

Code

pip install agi-diy
agi login
agi run act/so101 --probe -n 1

Needs Python 3.12 — LeRobot is installed on first use, requires 3.12 or later and does not run on 3.14 yet.

Or run a test call from the dashboard, or drive the simulated SO-101.

Licences and data

Checkpoint	vineetr196/act_so101_pickplace_v1 @ `acd8be4` · 198 MB	apache-2.0
Training data	vineetr196/so101_pickplace_v1	no licence declared

Licences as declared on the Hub at the pinned revision. Policies, explained.