Skip to main content

​
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 and Plans & limits.
  • 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.
  • Predictable plans — monthly credits, with published rate limits. See Plans & limits.

​
Base URL

The gateway lives at a single origin. Every endpoint is served under /v1.
API keys are created in the dashboard 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 for the details.
A first request (Anthropic-compatible)

​
Works with your agent

Each agent has its own page with the exact config. See all agents.

Claude Code

Codex CLI

Cursor

OpenClaw

Hermes Agent

opencode

Cline

Goose

​
Next steps

Quickstart

Key → base URL → first call, in three steps. One command for coding agents.

Claude Code

Run Claude Code on any model in the catalog with four environment variables.

API reference

Every endpoint on the unified surface, with request and response shapes.

Models

The full catalog: tiers, context windows and capabilities.

Migrating from another provider

Already calling OpenAI or Anthropic? It is usually two lines.

Troubleshooting

The failures people actually hit, and the one thing to change for each.