OmniRoute — Dashboard Features Gallery
Was this page helpful?
Loading OmniRoute...
Main README translations: 🇺🇸 English | 🇧🇷 Português (Brasil) | 🇪🇸 Español | 🇫🇷 Français | 🇮🇹 Italiano | 🇷🇺 Русский | 🇨🇳 中文 (简体) | 🇩🇪 Deutsch | 🇮🇳 हिन्दी | 🇹🇭 ไทย | 🇺🇦 Українська | 🇸🇦 العربية | 🇯🇵 日本語 | 🇻🇳 Tiếng Việt | 🇧🇬 Български | 🇩🇰 Dansk | 🇫🇮 Suomi | 🇮🇱 עברית | 🇭🇺 Magyar | 🇮🇩 Bahasa Indonesia | 🇰🇷 한국어 | 🇲🇾 Bahasa Melayu | 🇳🇱 Nederlands | 🇳🇴 Norsk | 🇵🇹 Português (Portugal) | 🇷🇴 Română | 🇵🇱 Polski | 🇸🇰 Slovenčina | 🇸🇪 Svenska | 🇵🇭 Filipino | 🇨🇿 Čeština
context-relay. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.
tuple is unique now influences runtime execution/fallback order for top-level combo steps
Playground (format converter), Chat Tester (live requests), Test Bench (batch tests), and Live Monitor (real-time stream).
Context Relay documentation.
assigned to routing combos; the default stacked math reaches average and eligible-context savings when both engines applyCompression Guide, RTK Compression, and Compression Engines.
) routes through , honoring provider-level and global proxy settings errors on Node.js 22) to prevent accidental exposure when sharing screenshots or recording demos. The full email address remains accessible via hover tooltip ( attribute).
catalog) — Shows at a glance how many models are enabled vs total. Automatically detects and repairs:
keeps your DB and configurations in . |
|
| erases all configurations, keys, and databases. |
shuts down Next.js cleanly, preventing SQLite WAL database locks (v3.6.2+) for full documentation.
OpenAI-compatible WebSocket clients via the upgrade endpoint. The custom server wraps Next.js and upgrades WS connections to full bidirectional streaming sessions. Authentication uses the same API key or session cookie as HTTP requests.
scoped sync tokens:
— Issue a new sync token (scoped, with optional expiry)
— Revoke a token
— Download a versioned, ETag-keyed JSON snapshot of all non-sensitive settings (passwords redacted)
. Consumers compare the response header to detect changes without re-downloading the full payload.
GLM Thinking () is now a registered first-class provider: 65 536 max output tokens, 24 576 thinking budget, 900 s default timeout, Claude-compatible API format, and shared usage sync with the GLM family.
Hybrid token counting also lands in v3.6.6: when a Claude-compatible provider exposes , OmniRoute calls it before large requests with graceful estimation fallback.
) — Blocks private/loopback/link-local IP ranges before the socket is opened.
- Safe fetch wrapper (
) — Applies the URL guard, normalises timeouts, and retries transient errors with exponential backoff.
) and are written to the compliance audit log via .
automatically retry when an upstream provider returns a model-scoped cooldown. Configurable via (default: 2) and (default: 30 s). Rate-limit header learning improved across , , and — per-model cooldown state is visible in the Resilience dashboard.
.