1 credit = $0.001, plus a markup on model costs. Team balance + monthly cap. Set the cap in Settings → Team → Wavo Limits. Stripe top up.

Wavo credits and limits

Wavo usage is metered in credits: 1 credit = $0.001. Each message is charged at input cost + output cost per 1K tokens (per the mode you pick) with a markup applied on top of base provider cost. The exact per-message credit charge is always shown in Settings → Team → Billing — treat that page as the source of truth. Owner / admin set the monthly cap in Settings → Team → Wavo Limits. Top up via Stripe from the billing page.

Who is this for

Anyone wondering "how much does Wavo cost?" or "why am I out of credits?". Admins managing team usage caps.

The pricing model

Per-message cost

Each Wavo message charges based on:

• Input tokens × input_cost_per_1k (model-specific)
• Output tokens × output_cost_per_1k (model-specific)
• MARKUP: a multiplier applied on top of the base provider cost

Formula:

cost_credits = (input_tokens × input_cost + output_tokens × output_cost) × markup

Stored in chat_message.credits_used per message. The markup multiplier is set by Wevion and can change over time, so the exact credits charged for each message are always shown in Settings → Team → Billing — treat that page as the source of truth, not any fixed number quoted elsewhere.

Mode costs (verified chat-models.ts)

You pick a mode (Fast / Smart / Expert), not a model name — Wevion manages which model powers each mode. Approximate base cost per 1K tokens in credits (input / output), before the MARKUP multiplier:

These are credit values per 1K tokens (1 credit = $0.001). The MARKUP multiplier is applied on top when charging; the exact per-message credit charge appears in Settings → Team → Billing.

Why some modes cost more

• Expert: deepest reasoning, best for complex analysis + long multi-tool chains — the most expensive lane
• Smart: balanced, everyday analysis
• Fast: cheapest, best for simple questions at high volume — the default

Pick a mode per task. For most daily mediabuyer questions, Fast (default) is fine; switch to Smart or Expert for heavier analysis.

The credit_balance table

Each team has one credit_balance row:

Same model as Creative Hub credits (Understanding AI credits) but separate ledger entries for chat messages.

View balance + history

Settings → Team → Billing shows:

• Current balance (in credits + USD equivalent)
• Monthly usage vs cap
• Recent chat transactions (per-message cost, mode, timestamp)
• Top up button (opens Stripe)

Top up via Stripe

For Stripe-enabled workspaces:

1. Settings → Team → Billing → Top up
2. Pick amount or custom value
3. You're taken to Stripe checkout
4. Complete payment (confirm 3DS if required)
5. Once payment clears, your balance increments automatically

Visible in Settings → Team → Billing after payment completes (usually < 1 min).

Monthly cap (admin)

Owner / admin can set a cap to limit per-period usage in Settings → Team → Wavo Limits:

• Monthly cap (in credits)
• Reset date (typically the first of the month)

When monthly usage reaches the cap, chat messages are blocked with a "monthly cap reached" notice.

Reset: on the reset date, monthly usage returns to zero.

Per-user cap?

Currently: cap is per-team (owner-level), not per-individual-user. All team members draw from the same pool.

For per-user discipline: monitor usage in chat_message aggregations, or use Wevion roles to restrict who can use Wavo.

Cost-saving tips

Use a cheaper mode for iteration

• Iterate prompts in Fast mode (cheapest)
• Switch to Smart or Expert for final / important analysis

Per-session mode override via the mode picker in the chat composer.

Use project instructions

Setting context once via project instructions avoids re-typing context per session. Less input tokens = less cost.

Be specific in prompts

Vague prompt → Wavo follow-ups → multiple turns. Specific prompt → single turn, lower total cost.

Avoid unnecessary tool calls

If you already know the data, don't make Wavo re-query. Reference previous answer.

Memory facts persist context

Saving "ROAS target = 3 for ClientA" as a project fact means you don't restate it each session.

Limit output length

"In one sentence" or "Just the number" — reduces output tokens.

What charges, what doesn't

Failed messages

If a model call fails (provider outage, network):

• chat_message.status = failed
• credits_used = 0 (no charge for failed completions)
• Wavo says "I couldn't complete that — please try again"

Partial outputs may or may not charge depending on what reached the user (typical: charge for tokens streamed).

Compliance + audit

credit_transaction is append-only:

• Every charge: type + amount (negative) + chat_message_id reference
• Every top-up: type + amount (positive) + stripe_payment_intent_id
• Sort by date for monthly reports

For audit: export from /settings/team/billing → CSV.

Common surprises

• "Used 1000 credits in a day": long sessions with many tool calls in Expert mode add up; check usage breakdown
• "Monthly cap hit early in month": usage spiked (large project audit); raise cap or wait reset
• "Credit balance after top-up": Stripe webhook can take 1-2 min; refresh page
• "Failed messages charged me": typically no charge; if charged, check credits_used on the message + contact support if anomalous

Common issues

• 402 monthly_cap_reached: cap hit; admin raises cap or wait reset
• Out of balance: top up via Stripe
• Top up failed: Stripe 3DS required → use POST /confirm flow
• Different cost vs expected: model + length + tool calls all affect cost; review per-message breakdown in history

FAQ

How much does a Wavo message cost?

Wavo usage is metered in credits, where 1 credit equals $0.001. Each message charges for input tokens times the model's input cost plus output tokens times its output cost, with a markup applied on top. The formula is (input_tokens × input_cost + output_tokens × output_cost) × markup, and the result is stored in chat_message.credits_used. The markup multiplier is set by Wevion and can change, so the exact credits charged for each message are shown in Settings → Team → Billing.

Which Wavo mode is the default, and which is cheapest?

Fast is the default and the cheapest lane — right for most daily mediabuyer questions and high-volume iteration. Smart (Plus and up) adds balanced reasoning at a moderate cost. Expert (Pro and up) is the most capable and most expensive, suited to complex analysis and long multi-tool chains. You pick a mode, not a specific model — Wevion manages the underlying model behind each mode.

How do I top up Wavo credits?

On Stripe-enabled workspaces, go to /settings/team/billing and click Top up, pick an amount, and complete payment via Stripe checkout, confirming 3DS if required. A webhook then adds a credit entry and increments your balance, usually in under a minute. You can view your current balance and recent chat transactions on the same billing page.

Can I set a monthly spending cap for Wavo?

Yes. An owner or admin can set a per-team cap in Settings → Team → Wavo Limits, choosing a monthly cap (in credits) and a reset date. When usage reaches the cap, chat messages are blocked with a "monthly cap reached" notice, and usage resets to zero on the reset date. The cap is per-team, so all members draw from one pool.

Do failed Wavo messages charge me?

Generally no. If a model call fails due to a provider outage or network issue, the message is marked status = failed with credits_used = 0, and Wavo tells you it couldn't complete the request. Partial outputs may charge for tokens that were streamed to you; if a fully failed message appears charged, check credits_used and contact support.

Related articles

• Wavo privacy and data usage
• Wevion plans explained
• Understanding AI credits
• Wavo — your AI assistant in Wevion — complete guide