# Yellow and Black

> Yellow and Black runs AI models for robots on its GPUs, starting with vision-language-action (VLA) models such as π0.5. Open a session and run inference for a real robot or a simulation.

Stage: private preview. Install the Python SDK with `pip install "https://yellowandblack.dev/sdk/robot_inference_client-0.5.3-py3-none-any.whl"`, run `yb setup` once (or set `YB_API_KEY` to a project key), then open a session on a model listed by `yb models --ready`. The free `transport-demo` sandbox (placeholder actions, not a model) costs nothing. Every page below is plain markdown; every error has a code with a documented fix.

## Start here

- [Quickstart](https://yellowandblack.dev/docs/quickstart.md): Install the SDK, add your key, and send your first request to a model running on our GPUs, with no GPU of your own.
- [Guide for AI agents](https://yellowandblack.dev/docs/agents.md): How an AI coding agent should read these docs, get a key, handle errors, and check that a robot integration really works.

## Reference

- [Python SDK reference](https://yellowandblack.dev/docs/python-sdk.md): Every public class and method in robot-inference-client, the Python SDK, with the options that matter in a robot control loop.
- [Command line (yb)](https://yellowandblack.dev/docs/cli.md): The yb command for checking your key, listing models, running a test session, reading the docs and explaining errors from a terminal.
- [Robot data formats](https://yellowandblack.dev/docs/robot-contracts.md): The exact names, image sizes and position numbers each model expects from your robot, and the shape of the moves it sends back, taken from the code that checks them.
- [Errors](https://yellowandblack.dev/docs/errors.md): Every error code and every reason a session can end, with what it means, whether to retry, and how to fix it.
- [HTTP and WebSocket API](https://yellowandblack.dev/docs/http-api.md): Call the API directly, without the Python SDK. Authentication, errors, safe retries, every route, and the session stream.

## Policies

- [Billing and credit](https://yellowandblack.dev/docs/billing.md): You pay per request the model answers, from prepaid credit, capped by each session's max_spend_usd. What is charged, what is free, and how a session is settled.
- [Limits](https://yellowandblack.dev/docs/limits.md): The limits the service enforces today, such as message size, deadlines, open sessions and rate limits, and why each one exists.
- [Security and data](https://yellowandblack.dev/docs/security.md): What keys and session passes can do, how your data travels, what we keep and for how long, and how to report a security problem.
- [Questions and answers](https://yellowandblack.dev/docs/faq.md): Short answers about what Yellow and Black is, sessions, what you pay for, speed, supported robots, your data, and AI agents.

## Optional

- [All docs in one file](https://yellowandblack.dev/llms-full.txt): every page above, concatenated.
- [OpenAPI description](https://yellowandblack.dev/openapi.json): every HTTP route and schema.
- [Service status](https://yellowandblack.dev/v1/platform/status): current health of each model, as JSON.