> For the complete documentation index, see [llms.txt](https://docs.obitmc.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.obitmc.com/readme.md).

# Obit

Obit serves an **OpenAI-compatible inference API** at `https://relay.obitmc.com/v1`. Point any OpenAI client at that base URL: chat completions, streaming, the Responses API and tool calling.

{% content-ref url="/pages/fV0IPrPohaVmB1E54Qy0" %}
[Inference API quickstart](/inference-api/inference-api.md)
{% endcontent-ref %}

## Start here

* [**Inference API quickstart**](/inference-api/inference-api.md): base URL, keys, and a copy-paste request in curl, Python and JavaScript
* [**Models and pricing**](/inference-api/models-and-pricing.md): what is served, context windows, cached input, provider pinning
* [**Errors and streaming**](/inference-api/errors-and-streaming.md): error codes, how a stream ends, timeouts, cancellation
* [**Request parameters**](/inference-api/parameters.md): fields honoured, ignored or refused
* [**Tool calling and the Responses API**](/inference-api/tools.md)
* [**Use Obit with …**](/inference-api/use-with.md): setup guides for opencode, Codex CLI, aider, LiteLLM and more
* [**Where your prompt runs**](/inference-api/where-your-prompt-runs.md): which machines serve the public pool

API keys come from [wms.obitmc.com](https://wms.obitmc.com): register, create or join a team, then create a key. Service status is at [status.obitmc.com](https://status.obitmc.com), and there is a hosted chat UI at [chat.obitmc.com](https://chat.obitmc.com).

{% hint style="info" %}
The inference API is in **beta**. Report bugs, or features that would ease your transition, through your Obit contact or at <team@obitmc.com>.
{% endhint %}

## Legal

* [Terms of Service (Inference)](/terms-of-service-inference.md)
* [Privacy Policy (Inference)](/privacy-policy-inference.md)