LiteLLM owns the pipe. Nadir adds an auditable model-and-effort decision beside it. Cited from their docs, including where they win.
Questions answered on this page
What is the difference between Nadir and LiteLLM?
LiteLLM owns the pipe. Nadir adds an auditable model-and-effort decision beside it. LiteLLM is the most widely used open-source LLM gateway, around 62,000 GitHub stars. One endpoint, key management, budgets, spend tracking, failover. We run it inside Nadir's own backend.
How does LiteLLM decide which model to use?
Load-balancing strategies first: simple-shuffle on RPM/TPM, latency-based, usage-based, least-busy, cost-based. Since v1.94.x the beta auto_router/complexity_router maps each request to a SIMPLE / MEDIUM / COMPLEX / REASONING tier, by default with a sub-millisecond heuristic scorer over seven hand-weighted dimensions. An LLM classifier, the trained Heuristic v2, a hosted or self-hosted decision model, or your own plugin can replace it. Nadir decides from a trained difficulty classifier over the prompt, the candidate menu, policy, cache, context, and session economics.
What does LiteLLM do after the model answers?
By default, nothing: the routing classifier only picks the tier, and the tier model's answer is returned. An optional post-call LLM-as-a-Judge guardrail can score the response, then block or log it. 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 LiteLLM cost compared with Nadir?
LiteLLM: Free and self-hosted, zero markup. Enterprise adds SSO, audit logs, admin roles, multi-region and SLAs, with usage-based pricing quoted on request. Auto Router customization is metered by an add-on license; one tuned router stays free. 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 LiteLLM do well?
The most widely used open-source gateway, with an MIT core. Zero markup, air-gapped deployment, SOC 2 Type 2 and ISO 27001. More routing knobs to tune yourself, plus public router benchmarks and shadow evaluations.
Why pick Nadir over LiteLLM?
Their free default tier assignment is a hand-weighted keyword heuristic, and the trained Heuristic v2 is free on one router only. Nadir's Caliper router is ranked 9th on the independent RouterArena leaderboard at 75.84% accuracy, a measure of routing decisions, not of customer savings. Nadir runs beside an existing LiteLLM gateway, decision-only or as the native `nadir/auto` provider merged into LiteLLM's docs in September 2026, so you keep the gateway you have. You get a per-request receipt for model, effort, cache, policy, and economics, with an outcome endpoint for measured follow-through. 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 LiteLLM?
Keep LiteLLM 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 LiteLLM, 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 LiteLLM 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.