As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/openvla/

# OpenVLA (7B) and OpenVLA-OFT

Stanford / UC Berkeley / Toyota Research Institute, OpenVLA family. Status: legacy. Type: robotics model. Released: 2024-06-13.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `openvla/openvla-7b` |  | https://huggingface.co/openvla/openvla-7b |
| Hugging Face (OFT fine-tunes) | `moojink/openvla-7b-oft-finetuned-libero-spatial` |  | https://huggingface.co/moojink/openvla-7b-oft-finetuned-libero-spatial |
| GitHub |  |  | https://openvla.github.io/ https://github.com/openvla/openvla |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: image, text
- Output: action
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: mit

## Where it stands

- Newer robotics models in the registry since its release: 32. The 5 newest:
  - Praxis-1 (2026-09-30) https://postcutoff.com/m/praxis-1/
  - Helix 2.5 (2026-09-17) https://postcutoff.com/m/figure-helix-2-5/
  - UnifoLM-WLA-1.0 (2026-09-10) https://postcutoff.com/m/unifolm-wla-1-0/
  - Skild S1 (Skild Brain) (2026-08-25) https://postcutoff.com/m/skild-s1/
  - Generalist GEN-1.5 (2026-08-19) https://postcutoff.com/m/generalist-gen-1-5/
- Weights are public under a permissive licence (MIT).

## What stands out

- Open 7B generalist VLA beating a 55B closed model: Llama 2 7B backbone with fused DINOv2 + SigLIP vision, trained on ~970k Open X-Embodiment episodes; outperformed RT-2-X (55B) by 16.5% absolute success over 29 tasks with 7x fewer parameters, and fine-tunes with LoRA on consumer GPUs. Source: https://arxiv.org/abs/2406.09246
- OFT fine-tuning recipe (Feb 2025) (found after launch): OpenVLA-OFT (parallel decoding, action chunking, continuous actions, L1 loss) raised LIBERO average success from 76.5% to 97.1% and action throughput 26x; on bimanual ALOHA it beat pi0 and RDT-1B by up to 15% absolute. Source: https://arxiv.org/abs/2502.19645

## Notes

The most-downloaded open VLA checkpoint on HF (500k+ downloads at check time); widely used as a research baseline. Superseded in capability by pi0-family and newer open VLAs but still a standard reference. Release day: arXiv 2406.09246 v1 dated 2024-06-13 (HF repo created 2024-06-10).


Model page: https://postcutoff.com/m/openvla/