What is the latest version of pi-0.5?

The current shipped version of pi-0.5 is pi-0.5.

How much does pi-0.5 cost?

pi-0.5 has no published flat entry price. Free and open-source model weights and code (Apache-2.0)

What AI model does pi-0.5 use?

pi-0.5 runs primarily on pi-0.5.

← Robotics

pi-0.5

Name: pi-0.5
Author: Physical Intelligence

Physical Intelligence · #25 most active of 27 in Robotics

Compare →

Open-weight VLA policies that transfer across robot embodiments and novel homes.

Trust score · Mostly verified

2 data points checked · 2026-09-12

Model stack: DisputedEntry price: UnverifiableVersion: VerifiedHow this works →

Current version

pi-0.5

Entry cost

Free and open-source model weights and code (Apache-2.0)

Changes / 30d

The short answers

What is the latest version of pi-0.5?: The current shipped version of pi-0.5 is pi-0.5.
How much does pi-0.5 cost?: pi-0.5 has no published flat entry price. Free and open-source model weights and code (Apache-2.0)
What AI model does pi-0.5 use?: pi-0.5 runs primarily on pi-0.5.

Source: Physical Intelligence — www.physicalintelligence.company · Reusable under CC BY 4.0 — cite Tomorrow

Capabilities

cross-embodiment transfer
open-world generalisation
open checkpoints
vision-language-action model (VLA)
open-world generalization
knowledge insulation
flow matching
robotics control
fine-tuning support
remote inference
Vision-Language-Action (VLA)
Robotics Control
Open-world Generalization
Knowledge Insulation
Flow Matching
Fine-tuning Support
Remote Inference
Vision-Language-Action (VLA) model
Open-world generalization
Knowledge insulation training
Flow matching support
PyTorch support
Robotic control and manipulation
Fine-tuning on custom datasets
Remote inference via websocket
robot manipulation
fine-tuning
Robotic Vision-Language-Action (VLA) model
Flow matching head for training and inference
Fine-tuning support on custom datasets
robotics
vision-language-action
VLA
vision-language-action model
fine-tuning base model
flow matching head
vla
flow-based
flow-matching
robotics policy
VLA (Vision-Language-Action)
flow-based matching
open-source weights
flow-based VLA
VLA (vision-language-action)
Robot Manipulation
Open-Source
Fine-Tuning Support
vision-language-action (VLA)
robot control
open-source
generalization
Vision-Language-Action
Robotics Policy
Vision-Language-Action model (VLA)
Knowledge insulation
Robotic control
Flow-based matching
robotic foundation model
Flow matching head
Robotics policy
flow-based vla
flow-based model
vision-language-action (vla)
inference support

Pricing

Open Source
Weights and training/inference code available on GitHub / Hugging Face / Google Cloud Storage
Free

Entry price over time

1 of 39 points reconstructed from Internet Archive captures (hollow dots) — dated by capture, not by when we first saw the page. View a capture

4/3/2025 · $09/15/2026 · $0

Geek mode

Models under the hood

pi-0.5
Physical Intelligence
disclosed
pi-0.5-droid
Physical Intelligence
disclosed
pi-0.5-libero
Physical Intelligence
disclosed
pi05_base
Physical Intelligence
disclosed
π₀-FAST
Provider undisclosed
disclosed

Context window

—

Public API

Multi-model routing

Stack signals

pytorch
uv
python

Shared model stack

Other tracked products running on the same foundation models — a quick read on how much of the catalog moves when one of these models changes.

Fast+1 aliasCognition · 2 products
- Windsurf
- pi-0.5
pi-0.5Physical Intelligence · 1 product
- pi-0.5
pi-0.5-droidPhysical Intelligence · 1 product
- pi-0.5
pi-0.5-liberoPhysical Intelligence · 1 product
- pi-0.5
pi05_basePhysical Intelligence · 1 product
- pi-0.5

green disclosed · amber inferred · grey unattributed. Aliases are folded into one model; provider concentration counts only models with an established vendor.

Reported scale

Reference data. Each figure is whatever the source actually said — weekly users, downloads, revenue run-rate — with its own definition and date. These are not comparable between tools and are never used to rank anything.

No public usage figure on record for this product.

Also in Robotics

All Robotics

Apollo

Apptronik

General-purpose humanoid for logistics

Version: Apollo 2
Cost: Pricing is not publicly listed. Contact Apptronik for details.
Model: Gemini Robotics

Phoenix

Sanctuary AI

Teleoperation-trained dexterous humanoid

Version: 8th generation
Cost: Pricing is not publicly listed; contact sales for inquiries.
Model: Carbon control system

ROS 2

Open Robotics

The robotics middleware standard

Version: 2
Cost: Free and open source robotics middleware.
Model: DDS (Fast/Cyclone)

Atlas

Boston Dynamics

Electric humanoid for industrial work

Version: Electric Atlas
Cost: Pricing is not published (enterprise/quote-only).
Model: Large Behavior Models

Digit

Agility Robotics

Warehouse humanoid in production

Version: Digit 5
Cost: Pricing is not published (enterprise/quote-only)
Model: Agility Arc

Figure 03

Figure

Humanoid with in-house Helix VLA

Version: Figure 03
Cost: Pricing not published
Model: Helix

Change history

Aug 9, 2026first seenmodel
QA auto-correction: model stack updated to π₀-FAST after a unanimous jury read of the source page
PaliGemma backbone, pi-0.5, pi-0.5 VLA, π0.5π₀-FAST
source
Aug 7, 2026first seencapability
New capabilities: Robotic Vision-Language-Action (VLA) model, Flow matching head for training and inference, Fine-tuning support on custom datasets
275
source
Aug 6, 2026first seencapability
New capabilities: robot manipulation, fine-tuning
256
source
Aug 5, 2026first seenmodel
pi-0.5 added π0.5 to its model stack
PaliGemma backbone, pi-0.5, pi-0.5 VLA, π₀.₅PaliGemma backbone, pi-0.5, pi-0.5 VLA, π0.5, π₀.₅
source
Aug 5, 2026first seencapability
New capabilities: Vision-Language-Action (VLA) model, Open-world generalization, Knowledge insulation training
178
source
Aug 4, 2026first seenmodel
pi-0.5 added π₀.₅ to its model stack
PaliGemma backbone, pi-0.5, pi-0.5 VLAPaliGemma backbone, pi-0.5, pi-0.5 VLA, π₀.₅
source
Aug 4, 2026first seencapability
New capabilities: Vision-Language-Action (VLA), Robotics Control, Open-world Generalization
107
source
Aug 3, 2026first seenversion
pi-0.5 moved to 0.5
pi-0.50.5
source
Aug 3, 2026first seenmodel
pi-0.5 added pi-0.5 to its model stack
PaliGemma backbone, pi-0.5 VLAPaliGemma backbone, pi-0.5, pi-0.5 VLA
source
Aug 3, 2026first seencapability
New capabilities: vision-language-action model (VLA), open-world generalization, knowledge insulation
37
source
Jun 10, 2026first seenmodel
pi-0.5 open checkpoints published in openpi
pi-0pi-0.5
source
Dec 4, 2025announcedmodel
pi-0.5 added pi-0.5 to its model stack
π0.5pi-0.5, π0.5
source
Dec 4, 2025announcedcapability
New capabilities: robot generalist policy, VLA, open-world generalization
3 tracked7 tracked · +robot generalist policy, VLA, open-world generalization, vision-language-action model
source
Dec 4, 2025announcedversion
pi-0.5 moved to pi-0.5
π0.5pi-0.5
source
Nov 5, 2025announcedversion
pi-0.5 moved to π0.5
0.5π0.5
source
Nov 5, 2025announcedcapability
New capabilities: Vision-Language-Action (VLA), Open-world generalization, Mobile manipulator control
5 tracked8 tracked · +Vision-Language-Action (VLA), Open-world generalization, Mobile manipulator control
source
Oct 15, 2025announcedversion
pi-0.5 moved to 0.5
π0.50.5
source
Oct 15, 2025announcedcapability
New capabilities: VLA, vision-language-action model, open-world generalization
5 tracked10 tracked · +VLA, vision-language-action model, open-world generalization, generalist policy, robot control
source
Sep 19, 2025announcedcapability
New capabilities: VLAs, Open-World Generalization, Mobile manipulator control
4 tracked9 tracked · +VLAs, Open-World Generalization, Mobile manipulator control, Physical world AI, Generalist robot policy
source
Aug 17, 2025announcedcapability
New capabilities: generalist policy, robot control
4 tracked6 tracked · +generalist policy, robot control
source
Jul 6, 2025announcedversion
pi-0.5 moved to π0.5
π0π0.5
source
Jul 6, 2025announcedmodel
pi-0.5 added π0.5 to its model stack
π0π0, π0.5
source
Jul 6, 2025announcedcapability
New capabilities: VLA, open-world generalization, robotics foundation model
4 tracked8 tracked · +VLA, open-world generalization, robotics foundation model, mobile manipulation
source
Apr 22, 2025announcedversion
pi-0.5 moved to pi-0.5
0.5pi-0.5
source
Apr 22, 2025announcedcapability
New capabilities: robotics, vision-language-action
30 tracked32 tracked · +robotics, vision-language-action
source
Apr 22, 2025announcedmodel
pi-0.5 added pi-0.5 to its model stack
π₀-FASTpi-0.5, π₀-FAST
source
Apr 22, 2025announcedcapability
New capabilities: VLA, vision-language-action model, fine-tuning base model
32 tracked35 tracked · +VLA, vision-language-action model, fine-tuning base model
source
Apr 22, 2025announcedversion
pi-0.5 moved to pi-0.5
0.5pi-0.5
source
Apr 22, 2025announcedmodel
pi-0.5 added to its model stack
pi-0.5, pi-0.5-droid, pi-0.5-libero, pi05_base, π₀-FASTpi-0.5, pi-0.5-droid, pi-0.5-libero, pi05_base, π₀-FAST
source
Apr 22, 2025announcedcapability
New capabilities: VLA (Vision-Language-Action), flow-based matching, open-source weights
40 tracked43 tracked · +VLA (Vision-Language-Action), flow-based matching, open-source weights
source
Apr 22, 2025announcedversion
pi-0.5 moved to pi-0.5
0.5pi-0.5
source
Apr 22, 2025announcedmodel
pi-0.5 added pi-0.5-droid, pi-0.5-libero to its model stack
pi-0.5, π₀-FASTpi-0.5, pi-0.5-droid, pi-0.5-libero, π₀-FAST
source
Apr 22, 2025announcedcapability
New capabilities: flow-matching, robotics policy
38 tracked40 tracked · +flow-matching, robotics policy
source
Apr 22, 2025announcedversion
pi-0.5 moved to 0.5
pi-0.50.5
source
Apr 22, 2025announcedcapability
New capabilities: VLA (vision-language-action)
44 tracked45 tracked · +VLA (vision-language-action)
source
Apr 22, 2025announcedcapability
New capabilities: Robot Manipulation, Open-Source, Fine-Tuning Support
45 tracked48 tracked · +Robot Manipulation, Open-Source, Fine-Tuning Support
source
Apr 22, 2025announcedcapability
New capabilities: flow matching head
35 tracked36 tracked · +flow matching head
source
Apr 22, 2025announcedversion
pi-0.5 moved to 0.5
pi-0.50.5
source
Apr 22, 2025announcedmodel
pi-0.5 added pi05_base to its model stack
pi-0.5, pi-0.5-droid, pi-0.5-libero, π₀-FASTpi-0.5, pi-0.5-droid, pi-0.5-libero, pi05_base, π₀-FAST
source
Apr 22, 2025announcedcapability
New capabilities: flow-based
37 tracked38 tracked · +flow-based
source

Subscribe to pi-0.5 changes

pi-0.5 compared

Straight head-to-head pages against the busiest products in Robotics.

pi-0.5 vs Apollo pi-0.5 vs Phoenix pi-0.5 vs ROS 2 pi-0.5 vs Atlas pi-0.5 vs Digit pi-0.5 vs Figure 03

How to cite this page

Free to cite and reuse under CC BY 4.0. Permalink: https://tomorrow.aliensquad.ai/tools/physical-intelligence-pi

APA

Tomorrow. (2026). pi-0.5 — version, pricing and model stack [Data set entry]. AlienSquad. Retrieved 2026-09-17, from https://tomorrow.aliensquad.ai/tools/physical-intelligence-pi

BibTeX

@misc{tomorrow-tools-physical-intelligence-pi,
  author       = {{Tomorrow}},
  title        = {pi-0.5 — version, pricing and model stack},
  year         = {2026},
  publisher    = {AlienSquad},
  howpublished = {\url{https://tomorrow.aliensquad.ai/tools/physical-intelligence-pi}},
  note         = {Accessed: 2026-09-17}
}