BYOK Costs

Ticket0 tracks estimated AI cost per task in ai_usage and surfaces breakdowns in Settings → AI → Cost Overview.

Typical cost profile per conversation

Most conversations include multiple small calls:

• classification/routing/language tasks (Flash or Haiku-class)
• draft generation (Sonnet-quality)
• optional retrieval and evaluation tasks

In practice, low-complexity conversations are usually a few tenths of a cent. Complex, long-thread conversations cost more because token usage is higher.

Model price assumptions used by the service

Ticket0 estimates cost from token usage with per-1M-token rates in the AI service:

• google/gemini-2.5-flash: $0.15 input / $0.60 output
• claude-3-5-haiku-20241022: $0.80 input / $4.00 output
• claude-sonnet-4-6: $3.00 input / $15.00 output
• text-embedding-3-small: $0.02 input

Cost formula

Estimated call cost:

(input_tokens * input_rate + output_tokens * output_rate) / 1_000_000

Conversation cost is the sum of all calls made for that conversation.

Optimization tips

• Keep KB content focused and deduplicated
• Raise auto-send thresholds only where needed
• Use lower-cost models for non-drafting tasks
• Trim very long historical context where possible
• Monitor high-cost task types in Cost Overview regularly

For setup details, see AI & BYOK.