Post-Cutoff.com
  1. Home
  2. Models
  3. π0.6 / π*0.6

π0.6 / π*0.6

Physical Intelligencelegacyroboticsπ (pi)

π0.6: ~5B-parameter VLA with a Gemma 3 4B backbone and ~860M-parameter action expert, keeps π0.5's hierarchical design (per model card, 2025-11-17, via search snippet). No weights or API. Superseded by π0.7 (2026-04). pi.website blocked automated fetches on 2026-09-29; details taken from search snippets of the blog/model card.

Input
text, image
Output
action, text
License
proprietary

How to call it

ProviderModel idEndpoint / URLDocs
None (internal to Physical Intelligence; model card and paper only)—www.pi.website/blog/pistar06docs

Notable capabilities (2)

Changelog: 2026-09-29 linked new entry 2025-11-17-physical-intelligence-pi-star-0-6-recap and arXiv 2511.14759.

Sources: π*0.6 blog, paper PDF, π0.6 model card, Humanoids Daily.

Timeline entry

  1. Physical Intelligence's π*0.6 learns from real-world experience with RL (Recap), running tasks for hours ★★★

    On 2025-11-17 Physical Intelligence released π*0.6, a version of its π0.6 VLA improved with Recap (RL with Experience & Corrections via Advantage-conditioned Policies): demonstrations, then human corrections, then RL on the robot's own autonomous trials. Recap more than doubled throughput and…

Other Physical Intelligence models

π0.7 · π0.5 · π0-FAST · π0 (pi-zero)