← All Business solutions
AICost Business Solutions

Customer service and support

3 AI automations this team runs today, each with the process, the AICost engine chain that prices and governs it, and the evidence behind it.

Cost engine Governance engine Each step priced and controlled. Click any engine to open its calculator or playground.
Ticket deflection with a self-service AI agentAgent assist with automatic case and call summariesVoice AI agent that answers the phone line

Ticket deflection with a self-service AI agent

Owner: Support operations / CX leader, with the knowledge-base owner

See a chain run live Build this chain for our stack
Scale: Gartner, as cited by Maven AGI: only 14% of service issues are fully resolved in self-service today

How the work runs

  1. Customer asks in chat, email or the help widget
  2. Agent searches the help center, macros and past tickets
  3. Agent looks up the order or account and drafts an answer or takes the action (status, reset, return label)
  4. Low-confidence, angry or refund/credit cases go to a human with a summary
  5. Ticket closed, tagged and checked for CSAT
  6. Knowledge gaps sent back to the content owner

AICost engine chain

5 cost engines 4 governance engines

Each step priced and controlled. Click any engine to open its calculator or playground.

Where cost leaks

  • Per-resolution or per-conversation vendor pricing grows with volume, even for questions customers re-ask
  • Long context from stuffing whole ticket histories and KB articles into every turn
  • Multi-turn loops when the agent cannot resolve and keeps retrying before handoff

Where risk sits

  • Made-up policy answers the company is held to (Air Canada had to honor a refund policy its chatbot invented)
  • Wrong refunds or credits issued through tool access
  • PII from the account or order exposed in the conversation or logs

Runs on

  • Zendesk
  • Salesforce Service Cloud
  • Intercom
  • Freshdesk
  • HubSpot
  • Kustomer
  • Shopify/order management

Evidence

businesswire.com ↗mavenagi.com ↗entrepreneur.com ↗

Agent assist with automatic case and call summaries

Owner: Contact center operations / workforce management

See a chain run live Build this chain for our stack
Scale: ServiceNow internal use: about 80% less time per resolution note

How the work runs

  1. Customer contacts a live agent
  2. AI listens or reads along and suggests answers and knowledge articles
  3. AI drafts the reply or next step for the agent to edit
  4. At wrap-up AI writes the case notes, disposition and follow-ups
  5. Agent reviews and saves to the CRM
  6. QA team samples summaries for accuracy

AICost engine chain

5 cost engines 2 governance engines

Each step priced and controlled. Click any engine to open its calculator or playground.

Where cost leaks

  • Summarizing every call, including short or duplicate ones, at full transcript length
  • Real-time suggestions firing on every utterance instead of at decision points
  • Per-seat add-on licences bought for agents who rarely use them

Where risk sits

  • Card numbers, health or account data copied from transcripts into CRM notes
  • Wrong or invented details in summaries becoming the record of what was agreed
  • Call recording and consent rules differ by state and country

Runs on

  • Salesforce Service Cloud
  • ServiceNow CSM
  • NICE CXone
  • Five9
  • Genesys
  • Amazon Connect
  • Zendesk

Evidence

servicenow.com ↗deloitte.com ↗nice.com ↗

Voice AI agent that answers the phone line

Owner: Contact center / customer experience leadership

See a chain run live Build this chain for our stack
Scale: Home Depot piloted in 50 stores in 2026; call volume not disclosed

How the work runs

  1. Customer calls and describes the issue in their own words (no phone menu)
  2. Voice agent identifies the reason for the call
  3. Agent checks order status, availability or account details through back-end systems
  4. Agent completes the task or sends a link by text
  5. Complex or upset callers are transferred to a human with context
  6. Call outcome logged and reviewed

AICost engine chain

4 cost engines 4 governance engines

Each step priced and controlled. Click any engine to open its calculator or playground.

Where cost leaks

  • Per-minute voice pricing (speech, model and telephony) on long or looping calls
  • Low-latency premium models used for every turn
  • Repeat calls when the agent fails and the customer calls back

Where risk sits

  • Hallucinated answers spoken aloud with no visible record for the customer
  • Identity verification and account changes done by voice without strong authentication
  • Customers who want a human and cannot reach one (Klarna moved back to more human agents)

Runs on

  • Genesys
  • NICE CXone
  • Five9
  • Amazon Connect
  • Google CCAI
  • Salesforce

Evidence

softwareseni.com ↗usefini.com ↗entrepreneur.com ↗

Reference chains are a starting point. Your volumes, models and vendors change the numbers; the engines recompute them from live prices.

Your process is not on the list, or runs differently? These chains are a starting point. We assemble the right engines for your workflow, your models and your vendors, and you run it over MCP or in the calculators.

Industry solutions → Build my chain
📖 Data sources & methodology 172 text models · 9 embeddings · 44 vision · 62 audio · 8 vector DBs across 10 vendor pages · last verified 2026-10-15

Methodology

  • All prices are USD per 1 million tokens, current as of 2026-10-15.
  • Vendor-published values have no mark. Inferred/extrapolated values are marked with * and listed below.
  • Batch API discounts are 50% off standard rates across providers that offer Batch mode.
  • Prompt caching discounts vary by provider (typically 80-90% off cached input tokens).
  • Regional data-residency surcharges (Anthropic 1.1x, OpenAI 1.1x, Google regional tiers) are NOT included in base rates.
  • Long-context pricing tiers apply when input exceeds model threshold.
  • Embedding prices are input-only (no output tokens generated).

Primary sources

Last-verified date is the most recent successful daily snapshot (aicost_pricing_snapshots) or, when no snapshot exists yet, the latest successful crawler run (aicost_crawler_runs). 10 of 10 vendors are currently verified. Aggregator services (TokenCost, AI Pricing Guru, etc.) are not listed.

Anthropic
2026-10-14
https://www.anthropic.com/pricing
Daily snapshot since Sep 2023 · 700 days captured
Anthropic Docs
2026-10-14
https://platform.claude.com/docs/en/about-claude/pricing
Daily snapshot since Sep 2023 · 700 days captured
OpenAI
2026-10-14
https://openai.com/api/pricing/
Daily snapshot since Sep 2023 · 701 days captured
Google AI
2026-10-14
https://ai.google.dev/gemini-api/docs/pricing
Daily snapshot since Dec 2023 · 676 days captured
Google Vertex
2026-10-14
https://cloud.google.com/vertex-ai/generative-ai/pricing
Daily snapshot since Dec 2023 · 676 days captured
DeepSeek
2026-10-14
https://api-docs.deepseek.com/quick_start/pricing
Daily snapshot since May 2024 · 615 days captured
xAI
2026-10-14
https://x.ai/api
Daily snapshot since Nov 2024 · 533 days captured
Mistral
2026-10-14
https://mistral.ai/pricing
Daily snapshot since Dec 2023 · 674 days captured
Cohere
2026-10-14
https://cohere.com/pricing
Daily snapshot since Sep 2023 · 700 days captured
Voyage AI
2026-10-15
https://docs.voyageai.com/docs/pricing

Inferred values (marked with * in calculator tables)

Derived from industry conventions, not directly published by the vendor. Typical conventions: cached input = 10% of base (90% off), Batch API = 50% of base (50% off).

Vendor / Model Field Why it’s inferred
Anthropic — Claude Sonnet 4.6 cachedInput Derived at 10% of input rate — Anthropic publishes 90% cache-hit discount on this tier.
Anthropic — Claude Sonnet 4.5 cachedInput Derived at 10% of input rate; same 90% cache-hit convention as Sonnet 4.6.
Anthropic — Claude Sonnet 4.5 batchInput Derived at 50% of standard input — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Sonnet 4.5 batchOutput Derived at 50% of standard output — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Haiku 4.5 cachedInput Derived at 10% of input rate — Anthropic 90% cache-hit discount convention.
OpenAI — GPT-5.4 Mini cachedInput Derived at 10% of input — OpenAI documents automatic 90% discount on cache hits across GPT-5.x tier.
OpenAI — GPT-5.4 Nano cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Nano batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Nano batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Pro batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.2 cachedInput Derived at 10% of input; no residency uplift.
OpenAI — GPT-5.2 batchInput Derived at 50% of input.
OpenAI — GPT-5.2 batchOutput Derived at 50% of output.
OpenAI — GPT-5 cachedInput Derived at 10% of input.
OpenAI — GPT-5 batchInput Derived at 50% of input.
OpenAI — GPT-5 batchOutput Derived at 50% of output.
OpenAI — GPT-5.5 Pro cachedInput Derived at 10% of input — OpenAI does not publish a cached rate for *-pro models; using the family convention.
OpenAI — GPT-5.5 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5.5 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5.2 Pro cachedInput Derived at 10% of input — pro-tier convention.
OpenAI — GPT-5.2 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5.2 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5.1 batchInput Derived at 50% of input.
OpenAI — GPT-5.1 batchOutput Derived at 50% of output.
OpenAI — GPT-5 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5 Nano cachedInput Derived at 10% of input.
OpenAI — GPT-5 Nano batchInput Derived at 50% of input.
OpenAI — GPT-5 Nano batchOutput Derived at 50% of output.
Google — Gemini 3 Flash cachedInput Derived at 10% of input — Google caching discount convention ~90%.
Google — Gemini 3.1 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
Google — Gemini 3.1 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 3.1 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Pro cachedInput Derived at 10% of input.
Google — Gemini 2.5 Flash cachedInput Derived at 10% of input.
Google — Gemini 2.5 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
Google — Gemini 2.5 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
xAI — Grok 4 (legacy) cachedInput Extrapolated at 25% of base.

Pricing is cross-verified against the LiteLLM community registry when available. Daily snapshots are kept in aicost_pricing_snapshots; every change is logged to aicost_price_changelog with old & new values for full audit trail. Read the full methodology →