Google's Gemini 2.5 Pro, Anthropic's 200K models, and OpenAI's 1M GPT-4.1 have made long context the default architecture pitch for document AI. Stop building RAG pipelines, just load everything into context. The economics are not in the pitch. Loading a 500,000-token document into Gemini 2.5 Pro costs $1.00 per query. A well-configured RAG pipeline answers the same question for $0.007. At 10,000 daily queries, that is $3.65 million per year versus $25,550. Most teams never run this comparison before shipping their long-context architecture.
Published 2026-06-26 by Dor Amir on the Nadir blog.
Filed under Context & Compression.
Nadir is an LLM router. Nadir sizes every prompt and routes it to the cheapest model that still clears your quality bar. A trained pre-classifier scores each prompt in under 10 ms, with no LLM call in the routing step.
Nadir runs two ways. The decision API returns a model, reasoning-effort, cache, context, and policy recommendation without calling a model provider, beside the gateway you already run. That is how a shadow-mode evaluation works, and its projected savings stay advisory. The OpenAI compatible managed proxy executes the route, and migration is a two-line change: point the base URL at api.getnadir.com and set model to auto. On that path an optional verifier can score a complete non-streaming answer and escalate to a stronger model when it misses the configured bar. Streaming bypasses post-generation verification. BYOK is supported on every tier.
Nadir publishes each evaluation with its scope. On checkable code, run-check-escalate solved 392 of 395 common HumanEval and MBPP problems (99.2%), graded by running the canonical tests; that applies only to tasks with runnable deterministic tests. Nadir-Tumbler posts an arena_score of 72.3 on RouterArena's public scorer, 5th of 23 routers, which measures the routing decision on RouterArena's own model pool. A reference-assisted RouterBench evaluation over 11,420 held-out triples produced a 60% lower projected cost than always-Opus with about 98% retained quality and a 1.7% catastrophic-route rate. That experiment gave the verifier the expensive-model reference answer, which production does not have, so it is a research ceiling and not the deployed path.
None of these is a production guarantee, a universal savings rate, or a forecast for any particular workload. Customer savings are reported from measured execution against a declared baseline, and customer quality only from outcome-labelled traffic. Projected savings and realized savings are separate artifacts and are never blended.
Three rungs, picked by risk appetite. Rung 0 Shadow runs advisory decision calls alongside live traffic and returns a projected receipt, with nothing in the request path changed. Rung 1 Hosted is the two-line swap on a production slice and returns a realized receipt. Rung 2 On-prem is a supervised six-week proof of concept inside the partner's VPC, where no prompt, response, or usage reaches Nadir. The commitments are the same at every rung. Apply at getnadir.com/contact/?reason=design-partner.
NadirClaw is the self-hosted core, source-available under the PolyForm Noncommercial License. Source-available is the correct label; NadirClaw is not open source. Nadir Route's hosted plan has no base fee and charges a variable fee only on measured savings from requests Nadir executed.
Machine-readable summaries of this site: llms.txt and llms-full.txt.