Nadir vs Not Diamond · verified 28 October 2026

Not Diamond is the closest rival. Nadir differs on auditable adoption, optional execution, and self-hosting. Cited from their site, including where they win.

Questions answered on this page

What is the difference between Nadir and Not Diamond?
Not Diamond recommends a model and stops there. Nadir can also run the request and check a complete answer, with a receipt for every decision. Not Diamond is an intelligent model router for coding agents: a decision layer, explicitly not a gateway, that recommends a model and reasoning effort for each step and runs through your existing harness and gateway.
How does Not Diamond decide which model to use?
A trained router predicts the best model and reasoning effort for each step, from payload semantics, KV cache state, session outcomes, sub-agent architecture, compaction events and the sequence of past turns. Reinforcement learning updates it from feedback signals. The prediction is made before each turn. Nadir decides from a trained difficulty classifier over the prompt, the candidate menu, policy, cache, context, and session economics.
What does Not Diamond do after the model answers?
Nothing. The router recommends a model and a reasoning effort, then your harness runs it and ships whatever comes back. Feedback signals tune later recommendations, not this answer. Nadir's decision-only mode returns before generation. On the managed, non-streaming path a complete response can enter a reference-free verifier and escalate when it misses the configured bar. Streaming bypasses that post-generation cascade.
What does Not Diamond cost compared with Nadir?
Not Diamond: $0.05 per million tokens routed, pay as you go (by application), plus an enterprise tier with volume discounts. Nadir has no base fee. Credits for Nadir-managed keys draw down at provider list price, with a 5.5% platform fee (8% on Business) added when you buy them. On your own keys, your provider bills you directly and Nadir adds no fee. Routing savings carry no fee, and shadow and recommendation-only deltas are advisory estimates that are never billed.
What does Not Diamond do well?
Session and KV-cache awareness across long agent runs. Reinforcement learning from real session outcomes, not just offline evals. SOC 2 Type II, ISO 27001 and payload-free routing.
Why pick Nadir over Not Diamond?
Nadir supports a shadow-to-enforce workflow with decision receipts, customer-declared baselines, governance, and optional proxy execution. The same API can recommend context compaction and cache policy alongside model and reasoning effort. For complete non-streaming responses, Nadir can add reference-free verification and escalation; for checkable code it can use deterministic tests. Nadir publishes no universal deployed savings or quality percentage. The 60% cost and 98% quality-preserved RouterBench result, measured on 11,420 held-out triples, is a reference-assisted research ceiling rather than the live reference-free path.
How do I trial Nadir against Not Diamond?
Keep Not Diamond exactly as it is. Write down the model, reasoning effort and monthly spend it produces today, and pick a week of real traffic, or a set of requests you can grade, as the baseline. Call Nadir's decision API from the same place that calls Not Diamond, in shadow mode. It returns the model, effort, cache and policy recommendation with no provider call, so nothing about execution changes. Read the receipts against what actually ran, and report outcomes through the outcome endpoint. Projected savings stay advisory until you execute a recommendation and report measured usage. Enforce on one workload, keep Not Diamond as the route you fall back to, and widen only when the outcomes clear your own bar.

What Nadir is

Nadir is an LLM router. Nadir sends each prompt to the cheapest model that can handle it. A small decision model reads each prompt against your model menu and picks the lowest-cost model it expects to handle it. When the decision model is uncertain or unavailable, the request goes to the strongest model on the menu. The routing step makes no call to your model provider.

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.

For coding agents, Nadir Auto is a terminal launcher for Claude Code or Codex that asks Nadir for the main-session model before each turn, with your configured model as the fallback and cost ceiling. Delegation integrations for Claude Code, Codex, or Cursor instead recommend a model tier for subagent work, and the agent decides; the Claude plugin can also move a main-thread turn to Haiku when Nadir's cache check prices it cheaper, unless its switch_main_model option is off. Either way inference runs on your own provider account, so Nadir holds no provider keys on that path.

What the numbers are, and what they are not

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.

Design-partner program

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 for a rung directly: Rung 0 Shadow, Rung 1 Hosted, or Rung 2 On-prem. Not sure which fits? Start at getnadir.com/contact/?reason=design-partner.

Licensing

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.

Pages on this site

Machine-readable summaries of this site: llms.txt and llms-full.txt.