AuroraDocs Hub

Get Aurora running in five minutes: install, set one provider key, send your first request, open the dashboard, and issue a managed key.

The five Aurora primitives every new user needs to know: providers, models, aliases, pools, combos, overrides, and workflows.

What is available in Aurora OSS and Aurora Enterprise, and how to start with the right edition.

All 14 providers Aurora auto-discovers, the env var that activates each, the default base URL, the default model list, and the link to the dedicated guide.

Expose stable model names, configure access rules, and manage provider model inventory from Aurora.

Manage pricing metadata used by usage analytics and cost reports.

Use user paths, provider names, models, and managed API keys to scope routing, access, workflows, and audit data.

Group compatible providers behind one pool for load balancing, failover, and pooled embeddings or generation calls.

Expose an ordered model fallback chain as one selectable model name.

Compress eligible tool output, prompts, and request concise completions to cut spend without changing how you call Aurora.

How workflow matching works, including user_path-first precedence and provider-name scoping.

Intercept and modify requests before they reach LLM providers.

How Aurora response caching works, how to enable exact and semantic cache layers, and what is included in the exact-cache key.

How Aurora forwards cache_control markers to upstream providers to reduce token costs, and which providers support it.

Configure Aurora failover with manual rules, understand experimental auto mode, and know when fallback attempts run.