Dokumentacja

Dokumentacja

Billing

Pay-as-you-go from a prepaid wallet. Every call is metered to the micro-cent and recorded in an immutable ledger. No subscription, no commitment, balance never expires.

Top up → balance sits in your wallet → each API call deducts its cost in real time. If your balance hits zero, calls return 402 insufficient_quota until you top up again.

To read the balance from a program, call GET /v1/balance. It returns the wallet, the amount held for tasks that are still running, and what is left under a monthly limit, and calling it costs nothing. See Balance.

The pricing model

For each call, Kunavo computes the user's cost as the larger of two numbers:

user_cost = max(catalog_cost, upstream_cost × markup_factor)
  • Catalog cost — the displayed price on the model card (per 1M tokens, per image, per second of video, etc.) × the actual usage units.
  • Upstream cost — what the provider charged Kunavo for that call.
  • Markup factor — Kunavo's margin on that cost.

The max() ensures: (a) you never pay less than the advertised catalog price, and (b) we never lose money on a call where the upstream cost spikes unexpectedly.

Billing units by modality

ModalityUnitGranularity
Chatper 1M input tokens + per 1M output tokensToken-exact; reasoning tokens billed at output rate.
Image (t2i / edit)per imagePer generated image; partial generations not charged.
Videoper videoFlat per-clip price, keyed by the resolution tier.

Long prompts bill at the vendor's long-context tier. On GPT-5.5, GPT-5.6 Sol and Terra, and GPT-6 Astra, a prompt over 272K input tokens bills the whole request at 2× input — cache reads and writes too — and 1.5× output, the tier OpenAI publishes. Claude has no long-context surcharge: its 1M context bills at the standard rate.

Cached tokens

Chat models cache stable prompt prefixes. Cache reads bill well below the normal input rate — 0.10× on Claude and OpenAI alike, and 0.025× on Claude Fable 5.1 and Claude Fable 5.2, 0.05× on Claude Opus 5.5. Cache writes bill at 1.25× input on every Claude model, 1-hour-TTL writes included (below Anthropic's 2×), and on GPT-5.6 Sol, Terra and Luna, and GPT-6 Astra; on every other model they bill at the plain input rate. Every class carries the model's own discount, so its cache prices sit at the same discount off the vendor's list as its input and output. The max() floor above is computed cache-aware, so the discount reaches you instead of being flattened by the catalog price.

See the Prompt caching guide for the full pricing table, how to enable cache_control, and how Kunavo's affinity routing keeps the cache warm.

Precision

All amounts in Kunavo are stored in micro_cents:

  • 1 USD = 100,000,000 micro_cents
  • 1 cent = 1,000,000 micro_cents
  • Minimum resolvable charge: 0.0001 cent ($0.000001). Practical chat calls often bill at this floor.

Dashboard display rounds to 6 decimals (USD) for small values and 2 decimals once it crosses cents. Internal accounting is exact.

Top-up

Fund your wallet at /app/billing. Top-ups are priced in US dollars, and checkout shows the payment methods on offer before you pay.

Your balance is credited once the payment is confirmed: by the payment provider, or on the network for a USDT or USDC transfer. If you have paid and your balance has not changed yet, please don't pay again.

Tier pricing

Top-upYou getBonus
$10$10.00—
$100$110.00+$10 (10%)
$1,000$1,200.00+$200 (20%)
$5,000$6,250.00+$1,250 (25%)
Balance never expires. Top up once, drain it over months. You can also set a monthly spend limit per API key from /app/keys for a hard ceiling on an individual workload: once that key's spend for the calendar month would pass the figure you set, its calls are refused with a 402 insufficient_quota and nothing is charged. Your other keys keep working. The same screen takes an IP allowlist per key — calls from anywhere else get a 403.

Key groups can carry a monthly spend limit too, set from the group's menu on /app/keys and counted over all of the group's keys: once a request would take the group's spend for the calendar month past it, the request is refused with a 402 insufficient_quota and nothing is charged. A key's own limit and its group's apply together, and whichever is reached first refuses the request. See Key groups.

Auto-recharge

Auto-recharge charges a saved card, so it cannot be switched on while card payments are being enabled.

The credit ledger

Every balance change is recorded in an append-only ledger:

TypeDirectionWhen
topupcredit (+)Payment confirmed.
consumedebit (−)API call billed at completion.
refunddebit (−)Paid balance returned to your payment method, with the bonus that came with it.
manual_adjustcredit (+/−)Operator correction (e.g. credit after an incident).

balance_after_micro_cents is stamped on each row, giving you a per-event snapshot. View the full history at /app/billing.

Usage logs

Every API call gets a row in usage_logs:

  • Model, status (success / error), HTTP status code
  • Input / output tokens, cached + cache-write tokens, image count, seconds, characters
  • cost_micro_cents — what you paid
  • Latency, request IP, user agent, API key prefix

Visible at /app/usage with filters and per-call detail pages.

Failed calls — do they cost anything?

No. Kunavo only bills on status = success. If the upstream returns 4xx / 5xx, or our task times out, the call is recorded but the cost is $0. We absorb the upstream cost ourselves rather than passing it through.

Refunds

Unused balance you paid for can be refunded at any time, without closing your account, to the payment method you paid with, less the payment processing fee. Balance already used on API calls, and bonus or promotional credit, are not refundable.

Request a refund in Billing → Refund unused balance, or by email to contact@kunavo.com. Requests are processed within 5 business days. Where a local payment method's refund window has passed, that part stays in your wallet and we contact you to arrange another way. The full rules are in the Refund Policy.

A charge we made in error, such as a pricing bug, is refunded in full, processing fee included.

Where to go next