Octo Small
Compact 27M variant of Octo. Faster inference on consumer GPUs, designed for low-latency control.
Octo Small is vla / robotics AI model from UC Berkeley, priced at €0.000 per 1M input tokens with a unknown context window.
0.7
Pricing
API Integration
Use our OpenAI-compatible API to integrate Octo Small into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("octo-small", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("octo-small", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("octo-small", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive — UC Berkeley / Stanford (Octo Model Team)'s Octo Small
Octo-Small is the compact 27M-parameter variant of the Octo generalist robot policy released by the Octo Model Team - a UC Berkeley + Stanford-led collaboration (Sergey Levine and Chelsea Finn labs) with contributors from Google DeepMind, CMU and Toyota Research Institute. Octo-Small was released alongside Octo-Base in May 2024 to give researchers a CPU/edge-friendly option that still benefits from the same 800k Open-X-Embodiment pretraining recipe. It is widely used in academic teaching, robotics coursework, and rapid prototyping where the 93M Base model is too heavy for the available hardware.
Visit UC Berkeley / Stanford (Octo Model Team) →Octo-Small is architecturally identical to Octo-Base but uses a smaller transformer trunk (~27M parameters total). Inputs are tokenised RGB observations from primary and wrist cameras and a T5-base-encoded language instruction, plus learnable readout tokens. The transformer fuses these tokens and emits action latents that are decoded by a diffusion head into continuous 7-DoF end-effector action chunks. It is pretrained on the same ~800k demonstrations from 25 Open-X-Embodiment-compatible datasets across 9 robot embodiments. Despite being ~3.4x smaller than Octo-Base, the small variant retains the diffusion-policy output and the embodiment-agnostic input adapters, making it suitable as a fast baseline and a starting point for fine-tuning to new robots on modest GPUs.
- Parameters
- 27M
- Context
- unknown
- Compact 27M generalist VLA policy
- Same training recipe and dataset as Octo-Base
- Continuous action chunks via diffusion head
- Runs on a single consumer GPU and many edge devices
- Fast fine-tuning on new robots / tasks
- Natural-language instruction conditioning
- Apache-2.0 open weights and code
- Reproducible baseline for academic VLA work
- Best for: edge robotics, teaching, fast iteration.
~800,000 cross-embodiment robot demonstrations from 25 Open-X-Embodiment datasets (same corpus as Octo-Base). Trained on TPU hardware with the public Octo recipe.
License: Apache-2.0 - fully open weights, code, and recipes. Research and commercial use permitted under the licence.
Known limitations
- Lower accuracy than Octo-Base and modern 7B VLAs
- Limited capacity for long-horizon language reasoning
- Trained at low image resolution (256x256)
- Few-shot transfer to drastically new robots still requires demos
- Single text encoder (T5) limits prompt richness
- No native multi-modal sensors beyond RGB
Frequently asked questions
Related Models
View all VLA / RoboticsGemini Robotics (2025)
Google DeepMind's vision-language-action model based on Gemini 2.0. Generalist robot policy with strong dexterity.
Gemini Robotics-ER
Embodied-reasoning variant of Gemini Robotics. Enhanced 3D spatial reasoning and trajectory planning.
Google RT-2-X
Google's VLA from RT-X collaboration. Trained on Open-X-Embodiment (22 robots, 527 skills), positive transfer.
LeRobot SmolVLA
HuggingFace's 450M VLA pretrained on 487 community LeRobot datasets. Runs on consumer GPUs.
Start using Octo Small today
Get started with free credits. No credit card required. Access Octo Small and 100+ other models through a single API.