The LLM router built for autonomous agents

Your agents run 24/7.
Your router should
think before it spends.

ROUTEXOR is the first BYOK routing layer designed for agentic workloads — cron jobs, sub-agent orchestration, and multi-step pipelines across 66+ models. Assign the right model to every task type. Set per-job budgets. Pay providers directly. Zero token markup.

Free tier included. No credit card required.

terminal
// agent cron job — runs nightly at 2am
r = client.chat.completions.create(
model="routexor/auto",
messages=agent_context,
task_profile="nightly-extract",
job_id="cron-doc-summarize"
)
profile: nightly-extract → claude-4-haiku
budget: $2.14 / $5.00 daily limit
routed via your Anthropic key · 180ms · $0.0001
routexor markup: $0.00

The routing tax killing your agent economics

Your agents burn tokens 24/7.
A 5.5% tax adds up to $66K a year.

Agents don't sleep. They run cron jobs, spawn sub-agents, and process chains around the clock. A percentage-based routing fee turns that volume into a six-figure annual tax — money that should be funding your next hire, not subsidizing a proxy.

Typical router
ROUTEXOR
Token markup
5.5% on all tokens
0%. Forever.
Monthly spend: $10K tokens
$10,550
$10,000 + $79 platform
Monthly spend: $100K tokens
$105,500
$100,000 + $79 platform
Annual routing cost at $100K/mo
$66,000
$948
Who holds your provider keys?
They do
You do
Cron job budget controls
No
Per-job budgets
Task-aware routing
No
Task profiles

Based on publicly listed pricing. 5.5% figure from OpenRouter's documented fee structure.

Without Routexor

Your agent's cron jobs default to the most expensive model — silently burning cash at 3am

Sub-agents inherit the parent's model even when a cheaper one would do

No way to assign different models to different task types in your pipeline

Provider goes down, your entire agent fleet goes down with it

No per-job budget limits — a runaway loop drains your balance before you wake up

Your routing provider holds your keys and takes 5.5% of every token

With Routexor

BYOK — your keys, your provider accounts, zero token markup on any agent workload

Task profiles assign the right model to every job type: cron, sub-agent, pipeline step

Per-job budget caps halt runaway agents before they drain your balance

Automatic failover — if Anthropic is down, your agent fails over to GPT, then Gemini

Real-time cost tracking per agent, per cron job, per task profile

Your keys stay encrypted in your vault. We route with them, we never own them.

Setup for agent builders

Three steps. Your agents route smarter tonight.

01

Plug in your provider keys

Add your Anthropic, OpenAI, Google, Mistral, or any provider API key to ROUTEXOR. We use them to make requests on your behalf. Billing goes straight to your provider account — we never see a cent of your token spend.

# Dashboard → Keys
anthropic_key = "sk-ant-..."
openai_key = "sk-proj-..."
google_key = "AIza..."
✓ Keys encrypted at rest. Billed to your accounts.
02

Define task profiles for your agents

Your nightly data extraction agent doesn't need Opus. Your reasoning chain does. Task profiles let you assign the right model to every job type — cron jobs, sub-agents, pipeline steps — each with its own fallback chain.

# routexor.config
{
"summarize": { model: "claude-4-haiku" },
"code_review": { model: "claude-4-sonnet" },
"deep_analysis": { model: "claude-4-opus" }
}
03

Budget every agent. Sleep through the night.

Every task profile gets a budget ceiling. When a cron job or sub-agent hits its limit, ROUTEXOR pauses it and alerts you — it doesn't silently keep spending. Your agents run at 3am. Your wallet doesn't have to worry.

# Per-job budget caps
{
"summarize": { budget: "$5/day" },
"code_review": { budget: "$50/day" },
"deep_analysis": { budget: "$200/day" }
}
! budget exceeded → job paused, alert sent
$750
burned in 3 days.

A real story from the agent builder community: an automated document processing agent running on a cron schedule defaults to the most expensive model. No task profile, no budget cap, no guardrails. The agent runs silently for three days. $750 gone.

Why this happens

1

No task profiles

Routers treat every request the same. A cron agent summarizing receipts gets the same model as your reasoning chain doing deep analysis.

2

No per-job budgets

Without spend limits per agent task, a misconfigured loop or spawned sub-agent can drain your entire balance before you notice.

3

No cron-aware routing

ROUTEXOR is the first router built for autonomous agents. Tag a request with a task profile and it gets routed to the right model, budgeted, and monitored — whether it runs once or on a cron.

ATERNA Partner Program

Early access to frontier models.
Before everyone else.

ROUTEXOR™ maintains direct partnerships with Anthropic, OpenAI, Google, xAI, and NVIDIA. Models marked Partner Preview are available on ROUTEXOR before general availability — giving your agents access to the latest capabilities while everyone else waits.

This isn't just a router. It's a privileged gateway to the frontier.

Claude Opus 4.6Partner Preview

Anthropic's most capable model. State-of-the-art reasoning, coding, and analysis.

GPT-5.4 ProPartner Preview

Premium tier GPT-5.4 for the most demanding enterprise workloads.

Gemini 3.1 ProPartner Preview

Google's latest frontier model. Advanced reasoning for complex agentic tasks.

Grok 4.20Partner Preview

xAI's latest model with rapid learning, multi-agent collaboration, and real-time X access.

Nemotron 3 SuperPartner Preview

NVIDIA's top model. #1 on SWE-Bench Verified for real coding tasks.

66
models available today

Every model your agents need. Every major provider. One endpoint. All at the provider's listed price — we add nothing on top.

Claude Opus 4.6Partner Preview
anthropic$25/1M out
Claude Sonnet 4.6
anthropic$15/1M out
Claude 4 Haiku
anthropic$4/1M out
GPT-5.4
openai$15/1M out
GPT-5.4 ProPartner Preview
openai$30/1M out
GPT-5.3
openai$8/1M out
GPT-5.2
openai$8/1M out
GPT-4.1
openai$8/1M out
GPT-4.1 Mini
openai$1.6/1M out
GPT-4.1 Nano
openai$0.4/1M out
OpenAI o3
openai$40/1M out
OpenAI o4-mini
openai$4.4/1M out
Gemini 3.1 ProPartner Preview
google$10/1M out
Gemini 3.1 Flash Lite
google$0.2/1M out
Gemini 3 Flash
google$0.4/1M out
Gemini 2.5 Pro
google$10/1M out
Gemini 2.5 Flash
google$0.6/1M out
Mistral Large
mistral$6/1M out
Mistral Small
mistral$0.3/1M out
Codestral
mistral$0.9/1M out
Llama 4 Maverick
meta$0.85/1M out
Llama 3.3 70B
meta$0.88/1M out
DeepSeek R1
deepseek$2.19/1M out
DeepSeek V3
deepseek$1.1/1M out
Command R+
cohere$10/1M out
Grok 4.20Partner Preview
xai$15/1M out
Grok 3
xai$15/1M out
Grok 3 Mini
xai$0.5/1M out
Sonar Pro
perplexity$15/1M out
Sonar
perplexity$1/1M out
Llama 3.3 70B (Groq)
groq$0.79/1M out
Llama 4 Maverick (Groq)
groq$0.6/1M out
Gemma 2 9B (Groq)
groq$0.2/1M out
Claude 3.5 Sonnet
anthropic$15/1M out
Claude 3.5 Haiku
anthropic$4/1M out
GPT-4o
openai$10/1M out
GPT-4o Mini
openai$0.6/1M out
OpenAI o3-mini
openai$4.4/1M out
OpenAI o1
openai$60/1M out
OpenAI o1-mini
openai$12/1M out
Gemini 2.0 Flash
google$0.4/1M out
Gemini 1.5 Pro
google$5/1M out
Gemini 1.5 Flash
google$0.3/1M out
Mistral Medium
mistral$2/1M out
Pixtral Large
mistral$6/1M out
Mistral Nemo
mistral$0.15/1M out
Llama 4 Scout
meta$0.4/1M out
Llama 3.1 405B
meta$3.5/1M out
Llama 3.1 70B
meta$0.88/1M out
Llama 3.1 8B
meta$0.18/1M out
DeepSeek Coder
deepseek$0.28/1M out
Command R
cohere$0.6/1M out
Qwen 2.5 72B
together$0.6/1M out
Qwen 2.5 7B
together$0.2/1M out
Qwen 2.5 Coder 32B
together$0.4/1M out
Nemotron 3 SuperPartner Preview
together$1.5/1M out
Nemotron 70B
together$0.88/1M out
WizardLM 2 8x22B
together$1.2/1M out
Hermes 3 70B
together$0.88/1M out
Yi Large
together$0.8/1M out
Sonar Reasoning
perplexity$5/1M out
Amazon Nova Pro
together$3.2/1M out
Amazon Nova Lite
together$0.24/1M out
Qwen 2.5 14B (Local)
ollama$0/1M out
Hermes 3 8B (Local)
ollama$0/1M out
Qwen 2.5 3B (Local)
ollama$0/1M out

You pay providers for tokens.
You pay us for the brain.

Flat platform fee. Zero token markup. Your provider invoices stay exactly what they'd be without us.

Free$0
1K requests/day · 3 provider keys · All models · Basic routing
Pro$79/mo
100K req/day · Unlimited keys · Task profiles · Per-job budgets · Priority support
EnterpriseCustom
Unlimited · Dedicated infra · SLA · Cognitive memory integration · Slack channel

The math: At $100K/mo in tokens, a 5.5% routing fee costs you $66,000/yr. ROUTEXOR Pro costs $948/yr. That's a $65,052 difference. Spend it on engineers, not routing tax.

Build agents that route smarter,
spend less, and never go down.

ROUTEXOR is in early access. Built for agent builders. Free tier included — no credit card, no token markup, no strings.