Billing & credits

Pay-as-you-go credits, top-ups, auto-reload, subscription plans, and enterprise invoicing.

Credits

Conduix bills in credits. 1 credit ≈ $1 of model spend. You buy credits in advance via Stripe, and every successful API call deducts the per-token rate of the model that served the request. Failures don't cost anything.

Watch your balance at /dashboard/billing and your per-model burn at /dashboard/usage.

Topping up

Buy credits one-off via Stripe Checkout. Five tiers — $5, $10, $30, $50, and $100 — with progressive volume discount (per-credit rate drops at larger tiers). Each top-up creates a Stripe invoice you can download from /dashboard/billing.

Auto-reload

Skip the "account paused" emails. Configure auto-reload to charge your saved card whenever your balance drops below a threshold:

Threshold: When to trigger (e.g. balance < 50 credits)
Reload amount: How many credits to buy each time
Card: Whichever payment method is on file with Stripe

Auto-reload only runs after the threshold is crossed, never speculatively. Toggle on/off from billing settings.

Subscription plans

Four self-serve plans plus custom Enterprise. Full breakdown at /pricing:

Explorer: Free tier — 3 credits to start, no card needed
Builder ($29/mo): 25 credits/mo, 60 req/min, audit log 7 days
Scale ($99/mo): 100 credits/mo, 240 req/min, audit log 30 days
Pro ($299/mo): 400 credits/mo, 1,000 req/min, per-key controls, 4h support, 180-day audit log
Enterprise (custom): SSO, dedicated CSM, 7-year audit log retention (SOC 2 planned; HIPAA/BAA in development)

Included credits roll into your wallet at the start of each billing period. Excess usage draws from your wallet (top-ups, auto-reload, or invoiced). Subscription credits reset monthly and don't roll over; top-up credits never expire.

Annual billing is available on Builder, Scale, and Pro at 17% off (two months free).

Enterprise — NET-30 invoicing

For volume customers who need PO numbers, custom MSAs, or DPA paperwork, Conduix offers invoice billing on NET-30 terms instead of card-on-file. Contact support@conduix.ai — we'll set up the customer record, mode-switch the org to billing_mode = "invoice", and route usage through monthly invoices.

Volume discounts. Custom unit pricing on Builder and Scale plans for committed monthly volume. Tell sales your projected spend and timeline; you'll get a proposal within 2-3 business days.

Spend caps

Hard caps per organization stop runaway spend before it happens. Configured at /dashboard/settings:

Daily cap: Hard ceiling per UTC day
Monthly cap: Hard ceiling per UTC month
Alert threshold: Warn at e.g. 80% of cap before blocking

When a cap is exceeded, requests fail with HTTP 402 spend_cap_exceeded — the provider call never runs. See Governance.

What an "insufficient credits" error looks like

HTTP 402 response

{
  "error": {
    "message": "Insufficient credits. Current balance: 12 credits.",
    "type": "insufficient_quota",
    "code": "insufficient_credits"
  }
}

Top up at /dashboard/billing or set up auto-reload to avoid this.

Cache hits are free

Identical deterministic requests (temperature: 0, same messages, same model) served from cache are not billed. Look for x-conduix-cache: HIT in the response headers.

Credits & tokens FAQ

How many tokens do I get per credit?

It depends on the model. Premium models cost more per token; budget models cost less. Using a typical 50/50 input-output mix, approximate tokens per credit:

Claude Opus 4 (frontier): ~17,800 tokens/credit
Claude Sonnet 4 (premium): ~89,000 tokens/credit
GPT-4o (premium): ~128,000 tokens/credit
Claude Haiku 4.5 (mid): ~333,000 tokens/credit
GPT-4o Mini (mid): ~2,130,000 tokens/credit
Gemini 2.5 Flash (mid): ~2,130,000 tokens/credit
DeepSeek V3 (budget): ~1,170,000 tokens/credit
Llama 3.3 70B / Groq (budget): ~1,160,000 tokens/credit

The same dollar buys ~100× more output on a budget model than on a frontier model. Use fallback chains and (Pro+) per-key model controls to route by cost as well as capability.

Why is the rate different per model?

We pass each model's token cost through directly. Claude Opus is the most capable model on the market and priced accordingly; GPT-4o Mini is optimized for routine, high-volume work at a much lower rate. You pick the right model for each use case — Conduix doesn't change the rates, and gives you one API across all of them.

Input vs output tokens?

Output tokens cost more than input tokens — usually 3–5× more. This is standard across every LLM provider. A typical chat message (~200 input, ~200 output) is roughly balanced, but workload type matters:

RAG / classification (long input, short output): cheaper per call
Chat / Q&A (balanced input/output): baseline cost per call
Creative writing / code generation (short input, long output): more expensive per call

Your dashboard at /dashboard/usage breaks down actual input:output ratio so you can see which workloads burn credits fastest.

What does a top-up actually buy me?

Concrete example using GPT-4o at ~400 tokens per chat message:

$5 top-up — 3 credits: ~960 chat messages, or ~96 blog drafts (4K tokens each)
$10 top-up — 7 credits: ~2,240 chat messages
$30 top-up — 25 credits: ~8,000 chat messages
$50 top-up — 45 credits: ~14,500 chat messages
$100 top-up — 100 credits: ~32,000 chat messages

Route the same dollars to DeepSeek V3 (budget tier) and multiply everything by ~9× more usage.

Subscription vs top-up: what's the actual rate?

Subscriptions give a better per-credit rate in exchange for monthly commitment:

Builder ($29 / 25 credits/mo): $1.16 per credit
Scale ($99 / 100 credits/mo): $0.99 per credit
Pro ($299 / 400 credits/mo): $0.75 per credit
Top-up $5 (3 credits): $1.67 per credit
Top-up $30 (25 credits): $1.20 per credit
Top-up $100 (100 credits): $1.00 per credit

Rule of thumb: if you're consistently topping up, the next subscription tier is cheaper per credit. If your usage is bursty or seasonal, top-ups keep you flexible.

Do credits expire?

Top-up credits: No expiration. Sit in your balance until used.
Subscription credits: Reset each billing cycle — unused credits don't roll over.

Subscription credits are an "included allotment" (think cell-phone minutes); top-ups are dollars-in-the-bank.

Can I see exactly how a call gets charged?

Yes. Every API call writes a usage log at /dashboard/usage with:

Model used: Including any fallback if primary failed
Input tokens: Tokens in the prompt
Output tokens: Tokens in the response
Credits charged: Total deducted for the call
Request ID: For audit + debugging

Retention by plan: Builder 7 days, Scale 30 days, Pro 180 days, Enterprise 7 years.

How do I estimate my monthly burn?

Top-down: Last month's LLM spend in dollars ≈ credits needed this month.
Bottom-up: Estimate calls × tokens × model rate from the table above.
Watch & learn: Start on Builder or Scale with auto-reload off. After 2 weeks of real usage you'll know which tier fits.

What happens when my credits run out?

API requests return 402 insufficient_credits. To resume:

Buy a top-up: Instant credit at /dashboard/billing
Enable auto-reload: Charges your card when balance drops below your threshold
Upgrade subscription tier: If you're regularly topping up

Failed requests don't consume credits. If a model errors out or you hit a rate limit, you're not charged.

Models & pricing Observability