One API for any VLA or world model
Send an observation from your robot or simulator, get an action chunk back. 10 models, one request schema, no per-model integrations.
Free to start · No credit card · Keys in 30 seconds
"model": "physical-intelligence/pi0", "instruction": "pick up the green cup and place it in the sink", "observation": { "image", "state" }
| t | x | y | z | roll | pitch | yaw | grip |
|---|---|---|---|---|---|---|---|
| 0 | +0.000 | +0.035 | +0.044 | +0.051 | -0.053 | -0.117 | 1.0 |
| 1 | +0.015 | +0.043 | +0.038 | +0.011 | -0.087 | -0.119 | 1.0 |
| 2 | +0.029 | +0.045 | +0.027 | -0.031 | -0.110 | -0.106 | 1.0 |
| 3 | +0.039 | +0.042 | +0.013 | -0.069 | -0.120 | -0.080 | 1.0 |
| 4 | +0.044 | +0.034 | -0.003 | -0.098 | -0.115 | -0.045 | 1.0 |
| 5 | +0.044 | +0.021 | -0.018 | -0.116 | -0.096 | -0.004 | 1.0 |
| 6 | +0.039 | +0.006 | -0.031 | -0.120 | -0.066 | +0.037 | 1.0 |
| 7 | +0.029 | -0.009 | -0.040 | -0.109 | -0.028 | +0.074 | 1.0 |
| 8 | +0.015 | -0.024 | -0.045 | -0.085 | +0.014 | +0.102 | 1.0 |
| 9 | -0.000 | -0.035 | -0.044 | -0.050 | +0.054 | +0.118 | 0.0 |
Built for the robots and simulators you already use
Every robot model is its own integration project
Today
- A different SDK, checkpoint format and runtime for every model
- Hand-written action-space conversion and normalisation per robot
- Your own GPUs to host each model, sized for peak load
- Weeks of glue code before you can compare two policies
With OpenRobotics
- One endpoint and one request schema for every VLA and world model
- Your robot’s action space mapped for you, per embodiment
- Hosted inference, billed per call, with spend limits per key
- Swap π0 for GR00T by changing one string
Observation in, actions out
Your first call in under a minute
- 1
Create an account
Email and password. Nothing else.
- 2
Create an API key
Name it, optionally cap its spend, copy it once.
- 3
Run the command
The snippet on the right works today: it checks your key and returns its remaining credit.
curl https://openrobotics.ai/api/v1/key \
-H "Authorization: Bearer $OPENROBOTICS_API_KEY"import os, base64, requests
obs = {
"image": base64.b64encode(open("wrist_cam.jpg", "rb").read()).decode(),
"state": [0.12, -0.48, 0.33, 0.0, 1.57, 0.0, 0.04], # joints + gripper
}
res = requests.post(
"https://openrobotics.ai/api/v1/act",
headers={"Authorization": f"Bearer {os.environ['OPENROBOTICS_API_KEY']}"},
json={
"model": "physical-intelligence/pi0",
"instruction": "pick up the red cup and place it in the sink",
"observation": obs,
"action_horizon": 50,
},
)
actions = res.json()["actions"] # 50 x 7 action chunkPick a policy. Switch any time.
π0
Generalist vision-language-action flow model trained on a large cross-embodiment robot dataset. Strong at dexterous, long-horizon manipulation.
π0.5
Co-trained on web data and heterogeneous robot data for open-world generalization to unseen homes and objects.
GR00T N1.5
Open foundation model for generalist humanoid robots with a dual-system architecture: a VLM for reasoning and a diffusion policy for motion.
Gemini Robotics
Gemini-based VLA that turns natural-language instructions into robot actions, with strong embodied reasoning.
OpenVLA 7B
Open-source VLA built on a Llama 2 backbone and trained on 970k Open X-Embodiment episodes.
Octo Base
Lightweight transformer-based generalist policy, fast to fine-tune on new observation and action spaces.
Give your robot a brain in one request.
Create a key and call any VLA or world model through the same endpoint.
Get an API key