> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sideren.io/llms.txt
> Use this file to discover all available pages before exploring further.

# One API. Every model. Built for agent loops.

> Sideren is a model API built for agents: point your tool at a single endpoint, authenticate with one key, and reach the entire Sideren model catalog through the protocols your stack already speaks.

## What is Sideren

Sideren serves its model catalog through a single gateway that is compatible with the
`OpenAI Chat Completions API`, the `OpenAI Responses API`, and the `Anthropic Messages API`.
Swap your base URL and key; keep the rest of your stack exactly as it is. Every model has
one public id: closed-weight models are called by their plain name (`gpt-6.1-sol`),
open-weight models are called `@sdn/<name>` (`@sdn/glm-5.3`). The older spellings
(`sdn-glm-5.3`, `glm-5.3`) keep resolving to the same model.

What you get on the other side of that swap:

* **The whole catalog, one key** — from fast, near-free small models to premium
  reasoning and vision. Each plan includes a set of models and higher plans add more; pay
  as you go reaches all of them. See [Models](/models) and
  [Plans & limits](/plans#model-access-by-plan).
* **The protocols agents speak** — Chat Completions, Responses and Messages, plus legacy
  Completions, embeddings, token counting and batches.
  Streaming on every chat dialect. Claude Code, Codex and the OpenAI and Anthropic SDKs
  work unmodified.
* **Sessions that keep moving** — if a model can't answer, the engine keeps your session
  moving instead of failing the turn. See [Reliability](/reliability).
* **Predictable plans** — monthly credits, with published rate limits. See
  [Plans & limits](/plans).

## Base URL

The gateway lives at a single origin. Every endpoint is served under `/v1`.

```
https://api.sideren.io
```

API keys are created in the [dashboard](https://www.sideren.io/dashboard/keys) and
start with `sdn_`. The Anthropic-style endpoints
accept the key as `x-api-key`; the OpenAI-style endpoints accept it as a bearer token. See
[Authentication](/authentication) for the details.

```sh title="A first request (Anthropic-compatible)" theme={null}
curl https://api.sideren.io/v1/messages \
  -H "x-api-key: sdn_your_key" \
  -H "content-type: application/json" \
  -d '{"model":"@sdn/gpt-oss-120b","max_tokens":256,"messages":[{"role":"user","content":"Hello"}]}'
```

## Works with your agent

Each agent has its own page with the exact config. See [all agents](/guides/other-tools).

<CardGroup cols={4}>
  <Card title="Claude Code" icon="https://mintcdn.com/layerx1/VcHszhDFLFcAsHzy/logos/claude-code.svg?fit=max&auto=format&n=VcHszhDFLFcAsHzy&q=85&s=dd653454701cd4d6a0407eb39b84f224" href="/guides/claude-code" width="24" height="24" data-path="logos/claude-code.svg" />

  <Card title="Codex CLI" icon="https://mintcdn.com/layerx1/VcHszhDFLFcAsHzy/logos/codex.svg?fit=max&auto=format&n=VcHszhDFLFcAsHzy&q=85&s=e440905921ad31e98989b29b653510ad" href="/guides/codex" width="24" height="24" data-path="logos/codex.svg" />

  <Card title="Cursor" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/cursor.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=d8591baa17e0abf699ed5e146232400f" href="/guides/cursor" width="512" height="512" data-path="logos/cursor.svg" />

  <Card title="OpenClaw" icon="https://mintcdn.com/layerx1/VcHszhDFLFcAsHzy/logos/openclaw.svg?fit=max&auto=format&n=VcHszhDFLFcAsHzy&q=85&s=c573cabaf072b58c0af396338ed9b7e4" href="/guides/agents/openclaw" width="24" height="24" data-path="logos/openclaw.svg" />

  <Card title="Hermes Agent" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/hermes-agent.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=caa286ccea44044bf35d800c99485163" href="/guides/agents/hermes-agent" width="256" height="256" data-path="logos/hermes-agent.svg" />

  <Card title="opencode" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/opencode.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=4e81cc0f9a1a2266c6f97353cb93cdb4" href="/guides/agents/opencode" width="512" height="512" data-path="logos/opencode.svg" />

  <Card title="Cline" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/cline.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=dd6594d28f0f5f02d320832c375d5f6d" href="/guides/agents/cline" width="1024" height="1024" data-path="logos/cline.svg" />

  <Card title="Goose" icon="https://mintcdn.com/layerx1/y35JAB8F72zDZrJE/logos/goose.svg?fit=max&auto=format&n=y35JAB8F72zDZrJE&q=85&s=59646795942d45b0c4ca2a089893f2d7" href="/guides/agents/goose" width="1648" height="1648" data-path="logos/goose.svg" />
</CardGroup>

## Next steps

<CardGroup cols={2}>
  <Card title="Quickstart" href="/quickstart">
    Key → base URL → first call, in three steps. One command for coding agents.
  </Card>

  <Card title="Claude Code" href="/guides/claude-code">
    Run Claude Code on any model in the catalog with four environment variables.
  </Card>

  <Card title="API reference" href="/api/overview">
    Every endpoint on the unified surface, with request and response shapes.
  </Card>

  <Card title="Models" href="/models">
    The full catalog: tiers, context windows and capabilities.
  </Card>

  <Card title="Migrating from another provider" href="/guides/migrating">
    Already calling OpenAI or Anthropic? It is usually two lines.
  </Card>

  <Card title="Troubleshooting" href="/support">
    The failures people actually hit, and the one thing to change for each.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.