Skip to main content

AI Credits

AI usage on SendSeven is measured in AI credits: messages written by AI bots and Conversational Agents, the tools they use, and AI features for your team. AI credits draw from the same monthly included pool as your messages and campaign sends. Beyond the pool, one AI credit costs EUR 0.01.

AI credits are available on Professional, Scale and Enterprise. Basic and API Only do not include AI features.

What costs AI credits​

UsageAI credits
Each message an AI bot or agent sends (answers, the Live Chat greeting, follow-ups)1 per message, on top of the normal message charge
Knowledge Base lookup that returns results+1
Web search+3
Reading an image the contact sent+2
Live refresh of a Knowledge Base page+1
AI agent builder: one successful build100

Counting is per message, not per conversation turn: a greeting followed by an answer is 2 credits, plus any tools used.

Free:

  • Knowledge Base lookups that find nothing, and lookups that fail.
  • Messages sent after a failure on our side, such as the apology, fallback or hand-over notice.
  • Understanding the contact's intent before answering.
  • Keyword bots and Flow send nodes. They pay the normal message charge only. Exception: the greeting a Keyword Bot sends when it starts a Live Chat session costs 1 AI credit, like any bot greeting.
  • The agent test console and bot test chats.

AI features for your team (reply suggestions, similar tickets, Team Chat /ai) and AI generation of WhatsApp Flows also use AI credits.

Usage breakdown API​

GET /api/v1/billing/tenant-usage returns the usage of each workspace on your billing account, including an ai_credits breakdown.

ParameterValues
scopeaccount (every workspace on the billing account) or tenant (the current workspace).
period0 = current month to date, 1 = last closed month, 2 = the month before.

Requires the billing:read scope. You must also be the billing account owner or have the account:billing_read permission; otherwise the API returns 403.

ai_credits appears once per workspace (tenants[*].ai_credits) and once at the top level for all listed workspaces:

"ai_credits": {
  "quantity": 1240,
  "amount_eur": 12.4,
  "unit_price_eur": 0.01,
  "bot_messages": {
    "quantity": 900, "amount_eur": 9.0,
    "by_charge": {"bot_message": {"quantity": 900, "amount_eur": 9.0}}
  },
  "tool_usage": {
    "quantity": 310, "amount_eur": 3.1,
    "by_charge": {
      "kb_lookup": {"quantity": 250, "amount_eur": 2.5},
      "web_search": {"quantity": 60, "amount_eur": 0.6}
    }
  },
  "other": {
    "quantity": 30, "amount_eur": 0.3,
    "by_charge": {"agent_assist": {"quantity": 30, "amount_eur": 0.3}}
  }
}
Bucketby_charge keys
bot_messagesbot_message
tool_usagekb_lookup, web_search, image_analysis, kb_live_refresh, tool
otheragent_assist, whatsapp_flow_ai, agent_builder, unlabeled (older usage without a label)
  • Only keys with usage are present.
  • quantity is in AI credits, not messages: a reply from a Conversational Agent on model_tier: advanced ("Deeper thinking") counts 2 under bot_message.
  • bot_messages + tool_usage + other equals quantity and amount_eur.
  • The totals match the AI credits category elsewhere in the same response: counts.kb_query and gross_by_type.kb_query. The category key is kb_query for compatibility; it means AI credits.
  • Amounts are gross, before the included pool. The pool is applied once for the whole billing account, so it is not split across these buckets.
  • ai_credits is null if the breakdown could not be computed. The totals in counts stay correct.

Next steps​