| What it does | LLM router that recommends the lowest-cost model for each task
| Open-source runtime for computer-use agents
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Not given
| Open source
|
|---|
| Pricing | Free: first 50 requests per month. Pay as you go: $0.002 per request, drawn from prepaid balance topped up by card in $5 multiples ($5 covers 2,500 requests). Business: $0.002 per request plus organizations and signed DPA on request. Enterprise: negotiated per-request rate with invoicing and custom
| Not given
|
|---|
| Key features | - Decision receipt recording model, reasoning effort, cache, context, policy, and economics
- Support for Anthropic Claude, OpenAI GPT, and Google Gemini models
- OpenAI-compatible managed proxy
- Bring-your-own-keys (BYOK) on every plan
- Complexity analysis via lightweight ML model
- Per-tier fallback chain for provider availability
- Organization-level observability with Nadir Lens
- Verifier-gated cascade for optional post-generation verification
- Savings accounting and comparison against benchmark model
| - Works with any OpenAI-compatible model
- Ready-wait mechanism instead of fixed sleeps
- Batches actions and bounds model calls
- Desktop pause, resume and fork with memory
- MCP server for Claude Code and Cursor
- Graded rollouts for computer-use RL
- Works with full desktops
- Supports multiple sandbox providers
|
|---|
| What makes it different | - Runs beside existing gateway without replacement, preserving infrastructure
- Auditable path from shadow observation to reviewed enforcement
- No fee on model savings or percentage markup on model costs
- Decision receipt joins measured execution and customer outcomes
- Self-hosted NadirClaw available free for noncommercial use
| - 1.48x faster than Anthropic's computer-use reference loop on the same model
- 19 points more success than OSWorld's Qwen agent at same speed
- Reduces rollout time by 40-53% by eliminating unnecessary waiting
- Published benchmarks run same model on same desktops with reproducible results
- Works with any model and sandbox provider
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 25 ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 12 | 0 |
| Citation Flow (Majestic) | 31 | 0 |
| Referring domains (Majestic) | 71 | 0 |