ROUTING INFRASTRUCTURE / ONLINE

Spend less on
every Cursor turn.

One endpoint trims repeated context, selects the right capability, and keeps premium intelligence in reserve for the work that earns it.

~80%estimated model savings
Representative 5,000-request agent workload with 27.2% less payload, compared with Claude Sonnet 4.6 list pricing. Your results vary.
Start free See the 3-minute setup
OpenAI compatible Anthropic compatible No card to start
Cursor readyFewer billable tokens
01 / THE SYSTEM

Control plane for
agent intelligence.

Not another model catalog. Strix is the decision layer between your tools and every provider you trust.

01 / REQUESTAgent intent arrivesMessages, tools, mode, and task evidence
02 / CONTROLContext is right-sizedLive evidence stays; dead weight can leave
03 / ROUTECapability meets costHealth-aware providers with escalation ready
01

Intent routing

Classifies work into specialized lanes for coding, deep reasoning, review, research, writing, and visual engineering.

02

Payload efficiency

Removes stale context and oversized schemas while preserving the evidence your model actually needs.

03

Resilient egress

Health-aware provider ordering, circuit state, streaming pass-through, and automatic transient failover.

04

Measured savings

Compares the optimized request with a consistent premium baseline, then separates filtering, routing, and cache savings in your dashboard.

02 / SPEND LESS

Your coding tool sends
more than you think.

Cursor and other agents resend history, tool schemas, and large tool results on every turn. Then a premium model can price every retained input and output token. Strix cuts both sides of that bill: send less, then route the remaining work to the lowest-cost capable tier.

01

Send fewer tokens

Drops stale history, duplicate context, oversized tool results, and idle schemas before they become billable input.

02

Buy only what the step needs

Fast utility work stays on an efficient tier. Advanced intelligence is reserved for difficult reasoning and escalation.

03

Prove the difference

See tokens kept, tokens avoided, baseline cost, optimized cost, and savings by day, client, mode, and capability tier.

LIVE ESTIMATE

See the coding-agent bill before and after Strix.

Change request volume and workload shape. The baseline uses the same Sonnet 4.6 list price used by the product evidence pipeline; optimized routes use prices already tracked in this repository.

Workload
ESTIMATED MONTHLY CODING-AGENT SAVINGS$33382% less model spend

At 5,000 requests per month, this scenario drops the modeled bill from $405 to $72.

You keep$333estimated monthly savings
Baseline$405Sonnet 4.6 · $3 input / $15 output per MTok
Optimized$72filtered input + scenario route
Input avoided4,896tokens per request

27.2% measured Agent payload reduction in Strix telemetry. Uses 18,000 input and 1,800 output tokens per request. Estimate, not a guarantee; provider prices and workload mix change.

Pricing source: Anthropic Claude Platform pricing, accessed July 2026. Filter band source: repository evidence constants and measured Agent telemetry.

03 / WHAT CHANGES

The goal stays.
The dead weight does not.

Strix does not summarize away the task. It preserves the current goal, relevant evidence, required tool protocol, and forced tools. It reduces categories of context that do not help this step.

USER PROMPT
“Refactor provider failover, preserve streaming, and add regression tests.”
ROUTE → refactor-safe
PRESERVED
  • + latest user goal
  • + relevant file context
  • + recent tool evidence
  • + edit tools
ELIGIBLE TO REDUCE
  • − idle browser/MCP schemas
  • − duplicate messages
  • − oversized old tool output
  • − agent boilerplate

Required tools and matched tool-call history remain attached.

04 / BEHIND THE ROUTER

Real models.
One stable interface.

Strix maintains a changing, health-checked range of capable model families. Your client keeps one configuration while routing adapts to the work, availability, and cost.

01
AnthropicFrontier reasoning
02
OpenAIFast + frontier coding
03
GoogleMultimodal work
04
DeepSeekAgentic coding
05
Z.aiArchitecture + review
06
MiniMaxSpecialist recovery
WHY A RANGE?

Fast utility work should not pay for frontier reasoning. Difficult tasks can escalate, and unhealthy providers can fail over without changing your client.

ONE PUBLIC CONTRACT

You choose task-shaped lanes. Strix keeps provider identities, fallback order, and parameter compatibility behind the routing layer.

05 / GET STARTED

Create your workspace.
Get your key at the end.

Start Strix free during early access. We prepare your workspace, issue your first API key once, and walk you through connecting any supported coding client.

Start free Open Cursor modelsRead the quickstart
Free early access · no card required · setup in minutes
  1. 01
    Create your account

    Set up the workspace that owns your usage, keys, and settings.

  2. 02
    Copy your one-time key

    The full key appears after setup. Copy it then—it cannot be recovered.

  3. 03
    Connect your client

    Open Cursor Models directly, then add Auto and Quick as your everyday and fast modes.

06 / PRICING

Free platform access during early access.

No card or checkout. Bring your OpenRouter key and get every Strix optimization, budget, and usage insight from day one. OpenRouter bills model usage directly.

START NOWBRING YOUR OPENROUTER KEY

The complete Strix platform with your OpenRouter account

$0 during early access

Every Strix feature is included. No card or Stripe checkout.

  • Your OpenRouter key is encrypted and never shown again
  • OpenRouter bills your model usage directly
  • Routing, filtering, caching, budgets, and evidence
  • No fallback to a Strix key if your credential fails
  • Advance notice before any future platform charge
Start free
MANAGED BY STRIX

One prepaid balance without provider credential custody

OpenRouter cost + 30%

Approval and prepayment are required. There is no subscription or seat fee.

  • Native OpenRouter request cost is the billing source
  • Manual prepaid balance with an auditable ledger
  • Same models, routing quality, and optimization
  • Explicit approval and funding controls
Request managed access
COST COMPARISON

See which funding mode fits.

Enter your expected native OpenRouter usage. Early-access BYOK has no platform fee; Managed adds 30% to measured provider cost.

LOWER ESTIMATED CUSTOMER COSTBYOKBased only on funding cost; both modes route identically.
BYOK total$100.00
Managed total$130.00
Native provider cost$100.00
Managed Strix fee (30%)$30.00

BYOK is free at the Strix platform layer during early access; customers pay OpenRouter separately. Managed totals use response-level native cost; catalog prices are estimates only. Taxes and OpenRouter account fees are excluded.