When Nadir helps most High volume, mixed complexity: If you're making 1000+ API calls/day and many are simple lookups, formatting, or basic Q&A, routing saves the most. On 11,420 RouterBench held-out triples, Nadir cuts cost 60% versus always-Opus while preserving 98% of always-Opus quality. Your savings will track that range when your prompt mix looks similar. Agentic workflows: Claude Code, Cursor, Aider - these tools make hundreds of calls per session. Many are simple (read file, check status). Routing + context optimization can cut costs 50%+. BYOK setups: When you bring your own API keys, Nadir just routes. You pay provider prices directly with zero markup. When to stick with one model All-complex workloads: If every prompt is a complex reasoning task (legal analysis, medical diagnosis), routing won't help. Everything stays on premium anyway. Latency-critical paths: The 50-100ms classification overhead matters if you're in a real-time pipeline where every millisecond counts. For most use cases, this is negligible. Small volume: If you're spending <$50/month on LLM APIs, the operational overhead of running Nadir isn't worth the savings. The math | Monthly spend | Prompt mix | Savings | Net after Nadir fee | |---------------|-----------|---------|---------------------| | $500 | 60% simple, 30% medium, 10% complex | ~$180 | ~$135 | | $2,000 | 40% simple, 40% medium, 20% complex | ~$640 | ~$480 | | $10,000 | 30% simple, 40% medium, 30% complex | ~$2,800 | ~$2,100 | Bottom line If your workload has a mix of simple and complex prompts, Nadir pays for itself from day one. If everything you do needs premium reasoning, save yourself the setup.