> Keiro Labs API documentation - Overview
> Page: https://docs.keirolabs.ai/
> Markdown: https://docs.keirolabs.ai/index.md
> Agent index: https://docs.keirolabs.ai/llms.txt
> API base URL: https://api.keirolabs.ai/v1
> Auth: send "Authorization: Bearer <api-key>" with a key created in the
> Keiro console (https://console.keirolabs.ai/api-keys). Use credentials saved by
> `keiro setup`, or resolve the key from a secret manager or an owner-only
> secret file and pass it to the client explicitly. Never read another
> provider's variable, and never put raw key material in environment
> variables, code, docs, or logs.

# Keiro API platform

Keiro is OpenAI-compatible. Change three lines in your existing client — the
base URL, your key, and the model — and you are running on eb1.

```text
https://api.keirolabs.ai/v1
```

Use one public base URL, a key created in the Keiro console, and a model ID
enabled for that key. Start with `eb1-preview` unless your workload has a clear
latency, cost, or frontier-quality requirement.

## Bring Keiro to your terminal

The Keiro CLI puts the model catalog in your shell and in your coding agent. Install it, authenticate once, then call eb1 from anywhere. [Install the Keiro CLI](sdks.md).

## Start

- [Make a first request](quickstart.md) - Install a client and print your first eb1 response.
- [Create or replace a credential](api-keys.md) - Create, rotate, and revoke API keys.
- [Choose a model](models.md) - Compare the four paid-beta IDs and the access on your key.
- [Use eb1 in a coding agent](sdks.md) - Point Codex, Claude Code, or Omnigent at the public model catalog.

## Build

- [Choose a client](sdks.md) - Official SDKs and the Keiro CLI.
- [Move an existing app](migration.md) - Repoint OpenAI-compatible code with a base-URL swap.
- [Call your functions](tool-calling.md) - Let the model call application tools.
- [Analyze images](images-vision.md) - Send images to a vision-capable model.

## API surfaces

The [API reference](api-reference.md) is the index for all public endpoints.

- [Responses](responses.md) - `POST /responses` - Typed input and output items — the newest compatibility shape.
- [Chat Completions](chat-completions.md) - `POST /chat/completions` - You already use message arrays and choices.
- [Messages](messages.md) - `POST /messages` - You already use top-level system and content blocks.
- [Models](api-reference.md) - `GET /models` - Account-scoped model discovery.

All completion surfaces support streaming. Tool and image features use the native request shape of each endpoint.

## Start building

- [Quickstart](quickstart.md) goes from key creation to a first response in a
  few minutes.
- [Models](models.md) compares the four public eb1 model IDs.
- Run your coding agent on eb1: [Claude Code](claude-code.md),
  [Codex](codex.md), or [Omnigent](omnigent.md).

## Operate an account

- [Usage and billing](usage-billing.md) explains console totals, request logs,
  exports, and pending versus finalized records.
- [Rate and spend limits](rate-and-spend-limits.md) documents limit headers,
  spend caps, and retry timing.
- [Errors](errors.md) lists machine-readable codes and stream-error fields.
- [Status and support](status-support.md) gives the safe incident-reporting
  path.

## Paid-beta boundary

The console manages organizations, keys, models, usage, billing, limits, and
support access. The local `keiro gui` command is for chat exploration only.

Public docs describe supported customer contracts. They do not expose or
promise private routing, provider selection, or operator interfaces.

## Trust and policy

Review [Legal and privacy](legal-privacy.md), [Data retention](data-retention.md),
[Beta SLA](beta-sla.md), and [Subprocessors](subprocessors.md) before sending a
sensitive workload. During the paid beta, supported API request and terminal
response payloads are retained by Keiro Labs to operate and improve the
service; see [Data retention](data-retention.md).