A
AXIOM Cloud
PORTAL
A

AXIOM CRM

Context Reasoning Manager — Intelligent LLM Gateway

One API endpoint. Five model tiers. Automatic complexity routing. Pay only for what you use — 75% of requests route to free models.

1
You send a prompt
Any OpenAI-compatible client
2
We classify complexity
Signal-based scoring in <1ms
3
Cheapest capable model
75% of requests route free

Five Intelligence Tiers

T0
TRIVIAL
Flash-Lite
FREE
Gemini Flash-Lite. Greetings, trivial math. Free cloud tier via Google, same model as T1 for ultra-trivial prompts.
"hello"
"what is 2+2"
T1
ROUTINE
Gemini Flash-Lite
FREE
File operations, boilerplate code, documentation, simple unit tests. Google's free tier handles 75% of daily coding work.
"list files in src"
"write a unit test"
T2
COMPLEX
Gemini Pro
$0.15 / 1M tokens
Debugging, cross-module analysis, build pipelines, firmware flashing. Supports tool calling for IDE integrations.
"debug the timeout"
"flash ESP32 to COM10"
T3
AGENT
Claude Sonnet 4
$3 / 1M tokens
Multi-step workflows, full-project refactoring, security audits. Anthropic's 200K context window for complex reasoning chains.
"refactor the entire auth"
"full rewrite of module"
T4
ARCHITECT
Claude Opus 4
$15 / 1M tokens
System architecture, distributed design, regulatory compliance (MaRisk, DORA, Basel). 1M context for the hardest problems.
"design distributed auth"
"MaRisk compliance audit"
94%
Average cost reduction vs single-model
75%
Requests routed to free tiers
<1ms
Classification overhead
$
Credit Balance
—
Loading...
~
Requests Today
—
Loading...
T
Active Tier
—
Most used model tier
K
API Keys
—
Active keys

Recent Transactions

TypeAmountDescriptionTime

Quick Actions

System Status

API Gateway Online
Database Connected
PROVIDER ROUTING
Loading…
Cache: loading…

Credit Packs

Pre-paid credits for LLM API usage. 1 credit = $0.01 USD.
Choose Payment Method
All transactions are secured. Credits are applied instantly after payment confirmation.
🔒SSL Secured
Secure card payment via Stripe. Supports Visa, Mastercard, Amex, and Apple Pay.
Pay with your PayPal balance or any card linked to your PayPal account. No card details shared with AXIOM.
Starter
1,000 credits
$10 USD
~220 T2 requests or ~22 T3 requests
Enterprise
10,000 credits
$100 USD
~2,200 T2 requests or ~220 T3 requests
🔒
256-bit SSL
Bank-grade encryption
⚡
Instant credits
Applied on payment confirm
🔄
No expiry
Credits never expire

Transaction History

Complete ledger of all credit operations
⬇ Export CSV
TypeAmountBalance AfterDescriptionTime

API Keys

Manage authentication keys for the AXIOM Gateway API
New API key created. Copy it now — it won't be shown again.
—
KeyLabelStatusLast UsedCreated

Integration Guide

Use your API key in the Authorization header:

# OpenAI-compatible endpoint
curl -H "Authorization: Bearer axk_your_key" \
     -H "Content-Type: application/json" \
     https://api.dexsi.com/v1/chat/completions \
     -d '{"model":"gpt-4o","messages":[{"role":"user","content":"hello"}]}'

The gateway automatically classifies complexity and routes to the optimal model (T0-T4). Credits are deducted based on actual token usage.

Usage Analytics

Request distribution, cost breakdown, and tier analytics

Requests by Tier — This Month

Loading…

Cost by Provider

Google
—
Anthropic
—

How the Tier Decision is Made

Every request passes through a 4-layer classification pipeline in under 1ms. No manual model selection needed — the system always picks the cheapest model that can handle your task correctly.

Layer 1 — Signal Scoring
Your prompt is matched against 100+ regex patterns. Each tier has its own signal list. Matches are weighted: T1 x1.0, T2 x2.0, T3 x2.0, T4 x3.0. Highest weighted score wins.
"debug" → T2
"refactor entire" → T3
"distributed" → T4
Layer 2 — Session Momentum
If you've been working at T3 for several turns, a simple follow-up like "what about tests?" stays at T3 instead of dropping to T1. Prevents jarring model switches mid-conversation.
hint = avg(last 15min)
score += 0.4 x hint
de-escalate after 3+ simple
Layer 3 — Token Floor
If the conversation exceeds 150K tokens, it's forced to T3 minimum regardless of signal score. Only Claude's 200K+ context window can handle payloads that large reliably.
if tokens > 150K:
  tier = max(tier, 3)
Layer 4 — Budget Guard
Before routing, the system checks if the provider has budget remaining. If exhausted, it falls back to a cheaper tier automatically. T4 → T3 → T2. Never fails silently.
Anthropic exhausted?
  T4 → T3 → T2
All gone? → HTTP 429
Your prompt → Signal score → + Momentum → Token check → Budget check → Model selected

The Five Tiers

T0
TRIVIAL
FREE
Gemini Flash-Lite. Ultra-trivial prompts routed to Google free tier. Same model as T1, zero cost.
T1
ROUTINE
FREE
Gemini Flash-Lite. File ops, docs, boilerplate, simple tests. Handles 75% of daily work at zero cost.
T2
COMPLEX
$0.15/1M
Gemini Pro with tool support. Debug, firmware, pipelines. 20x cheaper than Claude for mid-complexity.
T3
AGENT
$3/1M
Claude Sonnet 4. Multi-step agent workflows, full refactors, security audits. 200K context window.
T4
ARCHITECT
$15/1M
Claude Opus 4. System architecture, distributed design, regulatory compliance. 1M context for the hardest problems.

Settings

Account preferences and notification settings

Profile

Account Info

Account ID

—

Active

Member Since

—

Plan

Pay-as-you-go

⚡ PAYG

Rate Limit

60 requests / minute

Preferences

Low balance alert

Notify at support@dexsi.com when credits drop below 100

Weekly usage report

Email summary every Monday with spend + tier breakdown

Tier escalation alerts

Alert when requests route to T3/T4 (billed tiers)

Webhook Notification URL

Receive a POST request to your endpoint on credit top-up, low balance events, and high-cost request alerts.

Payload example: {"event":"credit.low","balance_cents":150,"tenant_id":42}

Danger Zone

Revoke all API keys

Immediately invalidate all active keys for this account

Export all my data

Download a full account data export (GDPR Art. 20)

Close account

Request account deletion. Unused credits are non-refundable per ToS.

Billing & Invoices

Payment history, receipts, and billing information
⬇ Export CSV
$
Total Spent
—
All-time top-ups
📅
This Month
—
Credits purchased
🏷
Current Balance
—
Available credits

Payment Methods

💳
Stripe Checkout
Visa, Mastercard, Amex, Apple Pay, Google Pay
🅿
PayPal
PayPal balance, linked cards & bank accounts

No card details are stored by AXIOM. All payments are processed by Stripe / PayPal.

Billing Info

Billing Model

Pay-as-you-go (pre-paid credits)

Currency

USD — 1 credit = $0.01

Stripe Customer ID

—

Refund Policy

Credits are non-refundable per ToS

Payment Receipts

Top-up transactions only
DateAmountCreditsMethodReferenceStatus

⚙ Admin Panel

Platform-wide management — visible to admin key only
👤
Total Tenants
—
Loading…
📊
Today Requests
—
Across all tenants
💰
Month Revenue
—
Credit top-ups (Stripe + PayPal)
🔑
Active Keys
—
Platform-wide

Manual Credit Adjustment

All Tenants

IDNameEmailBalanceStatusMember SinceActions

Help & Support

Documentation, FAQ, and contact information
📖
API Reference
Interactive Swagger docs for all endpoints
❓
FAQ
Answers to common questions
✉️
Contact Support
support@dexsi.com — 24h response

Quick Integration

AXIOM is fully OpenAI-compatible — no code changes needed. Just change the base URL and add your API key.

# For OpenAI Python SDK:
from openai import OpenAI
client = OpenAI(
  base_url="https://api.dexsi.com/v1",
  api_key="axk_your_key_here"
)
# For Claude Code:
claude config set apiBaseUrl https://api.dexsi.com

Service Level Agreement

99.5%
Uptime SLA
Cloud Run managed infrastructure
<1ms
Classification overhead
Routing decision cost
60 req/min
Rate limit
Per API key, sliding window
€5.00
Welcome credit
Applied on account creation

Frequently Asked Questions

Credits are deducted based on actual token usage × tier rate. T0 and T1 are always free. T2 (Gemini Pro) costs $0.15/M input + $0.60/M output tokens. T3 (Claude Sonnet) costs $3/M input + $15/M output. T4 (Claude Opus) costs $15/M input + $75/M output. A typical T2 debugging request (~2,000 tokens) costs ~0.3 cents.
T0 and T1 requests (free tiers) continue working regardless of balance. T2–T4 requests return HTTP 402 with {"error":"Insufficient credits"}. Your API client can catch this and prompt for a top-up. Purchase a new pack to resume instantly.
Yes. Each account can have multiple API keys with different labels (e.g., "laptop", "CI", "production"). All keys share the same credit balance and tenant ID. You can revoke individual keys without affecting others.
Every request is scored in under 1ms by a 4-layer classifier: (1) Signal scoring — 100+ regex patterns map keywords to tiers. (2) Session momentum — maintains context tier to avoid jarring switches mid-conversation. (3) Token floor — forces T3+ for payloads >150K tokens. (4) Budget guard — falls back to cheaper tier if provider budget is exhausted. You don't choose the model — AXIOM always picks the cheapest capable one.
Request/response content is not stored by AXIOM. Only metadata is logged (token counts, tier, timestamp, cost). Requests are forwarded to Google or Anthropic per their respective data processing agreements. AXIOM does not use your data for training of any kind.
Pre-paid credits are non-refundable. However, if there is a platform error that caused incorrect credit deductions, contact support@dexsi.com with the request timestamp and we will investigate and adjust manually.
Current routing: T0/T1 → Gemini Flash-Lite (free), T2 → Gemini Pro, T3 → Claude Sonnet 4, T4 → Claude Opus 4. Models are updated when better options become available. Rates are locked for 30 days after any model swap and communicated via email before change.
Email support@dexsi.com with your account email and a brief description of the issue. Response time is typically within 24 hours on business days. For billing disputes, include the transaction ID from your history page.

Legal

Terms of Service Privacy Policy Data Processing Agreement GDPR / Data Deletion

AXIOM Cloud is operated by Dexsi Systems. VAT ID available on request for EU customers.