Workflow designer

Start from an example

Pick a workflow close to yours, open it in the designer and change the words to fit your business. Back to the designer →

Customer supportCross-industryChat or help assistant

A support assistant that answers customer questions from our help center and order history, and hands hard cases to an agent. About 60,000 conversations a month.

Customer supportRetail and e-commerceAgent that takes actions

An agent that handles returns and refunds for shoppers: checks the order, applies the return policy, issues the refund and emails the label. 15,000 returns a month.

Customer supportCross-industryVoice line

A voice line that answers billing calls, verifies the caller, explains the bill and books a callback when it cannot help. 40,000 calls a month, about 4 minutes each.

Customer supportSoftware and SaaSTriage and routing

Triage every inbound support ticket: tag product area and urgency, detect angry customers and route to the right queue. 120,000 tickets a month.

Finance and accountingCross-industryDocument processing

An agent that reads supplier invoices, matches them to purchase orders and pays the clean ones. About 20,000 invoices a month, financial data.

Finance and accountingCross-industryInvestigation and analysis

Month-end close helper that reconciles bank lines against the ledger, explains breaks and drafts journal entries for review. 300,000 bank lines a month.

Finance and accountingBanking and fintechDocument processing

Loan application processing: read pay stubs, bank statements and IDs, pull the key fields and flag missing documents for an underwriter. 8,000 applications a month.

Finance and accountingBanking and fintechInvestigation and analysis

AML alert review: summarize each flagged transaction, pull customer history and draft a disposition for an analyst to approve. 25,000 alerts a month.

Sales and marketingCross-industryContent and media

Write personalized outbound emails from CRM and website data, three variants per prospect, with a person approving before send. 50,000 prospects a month.

Sales and marketingRetail and e-commerceContent and media

Generate product descriptions, SEO titles and two images for every new catalog item, translated into 5 languages. 6,000 products a month, public content.

Sales and marketingSoftware and SaaSNotes and summaries

Summarize every sales call, update the CRM fields and draft the follow-up email. 12,000 calls a month, about 30 minutes each.

HR and peopleCross-industryTriage and routing

Screen job applications against the role requirements, rank candidates and draft a short note for the recruiter. 40,000 candidate applications a month.

HR and peopleCross-industryChat or help assistant

An internal HR assistant that answers employee questions on benefits, leave and policies from our handbook. 20,000 questions a month, employee personal data.

Legal and complianceLegal servicesDocument processing

Contract review: read incoming NDAs and vendor contracts, compare clauses to our playbook and mark risky terms for an attorney. 3,000 contracts a month, privileged legal documents.

Legal and complianceCross-industryInvestigation and analysis

Map new AI regulations to our policies: read each regulatory update, find affected controls and draft the change for compliance sign-off. 400 updates a month.

Legal and complianceLegal servicesLong document drafting

Draft first versions of litigation briefs from case files and research memos, with an attorney reviewing every draft. 500 briefs a month.

IT and engineeringSoftware and SaaSCoding

A coding agent that fixes small bugs from tickets, writes the tests and opens a pull request for engineer review. 4,000 tickets a month.

IT and engineeringCross-industryAgent that takes actions

An IT helpdesk agent that resets passwords, grants software access by policy and answers how-to questions. 30,000 employee requests a month.

IT and engineeringSoftware and SaaSInvestigation and analysis

Incident investigation: read alerts, logs and recent deploys, find the likely root cause and post a summary to the on-call channel. 2,000 incidents a month.

Operations and supply chainManufacturingImage inspection

Inspect product photos on the production line, flag defects and send unclear cases to a quality engineer. 500,000 images a month.

Operations and supply chainLogistics and travelDocument processing

Read bills of lading, customs forms and delivery receipts, extract shipment fields and update the TMS. 70,000 documents a month.

Operations and supply chainManufacturingAgent that takes actions

A procurement agent that compares supplier quotes, checks contract terms and drafts purchase orders for approval. 5,000 requests a month, financial data.

Product and researchCross-industryInvestigation and analysis

Analyze customer feedback from reviews, tickets and surveys, cluster themes and write a weekly insights report. 200,000 feedback items a month.

Product and researchCross-industryChat or help assistant

An enterprise knowledge assistant that answers questions from Confluence, SharePoint and product docs with citations. 80,000 questions a month, internal data.

Customer supportHealthcareVoice line

A patient scheduling line that books, moves and confirms appointments and answers clinic questions. 25,000 patient calls a month, HIPAA data.

Operations and supply chainHealthcareNotes and summaries

An ambient clinical scribe that listens to the visit and drafts the note for the physician to sign. 40,000 patient visits a month, HIPAA data.

Finance and accountingHealthcareDocument processing

Prior authorization: read the clinical record, fill the payer form and flag missing evidence before a nurse submits. 10,000 requests a month, patient health data.

Operations and supply chainInsuranceDocument processing

Insurance claims intake: read the claim form, photos and police report, check coverage and route simple claims to fast-track. 30,000 claims a month, customer personal data.

Sales and marketingMedia and publishingContent and media

Turn each long article into social posts, a newsletter blurb and a short video script. 3,000 articles a month, public content.

Customer supportPublic sectorChat or help assistant

A public services assistant that answers resident questions on permits, taxes and benefits from official pages, in 6 languages. 100,000 questions a month.

HR and peopleEducationChat or help assistant

A student help assistant that answers course, enrollment and financial aid questions and books advisor time. 50,000 questions a month, student personal data.

Operations and supply chainLogistics and travelAgent that takes actions

A travel rebooking agent that rebooks passengers after cancellations by policy and sends the new itinerary. 20,000 disruptions a month, customer personal data.

Product and researchBiotech and pharmaInvestigation and analysis

A research assistant that reads internal lab reports and published papers, answers scientists' questions with citations and drafts literature summaries. 15,000 questions a month, confidential research data.

Legal and complianceBiotech and pharmaDocument processing

Clinical trial document review: check protocols and consent forms against the template and regulations, flag gaps for the regulatory team. 1,500 documents a month, patient health data.

📖 Data sources & methodology 172 text models · 9 embeddings · 44 vision · 62 audio · 8 vector DBs across 10 vendor pages · last verified 2026-10-18

Methodology

  • All prices are USD per 1 million tokens, current as of 2026-10-18.
  • 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
2026-10-18
https://www.anthropic.com/pricing
Daily snapshot since Sep 2023 · 704 days captured
Anthropic Docs
2026-10-18
https://platform.claude.com/docs/en/about-claude/pricing
Daily snapshot since Sep 2023 · 704 days captured
OpenAI
2026-10-18
https://openai.com/api/pricing/
Daily snapshot since Sep 2023 · 705 days captured
Google AI
2026-10-18
https://ai.google.dev/gemini-api/docs/pricing
Daily snapshot since Dec 2023 · 680 days captured
Google Vertex
2026-10-18
https://cloud.google.com/vertex-ai/generative-ai/pricing
Daily snapshot since Dec 2023 · 680 days captured
DeepSeek
2026-10-18
https://api-docs.deepseek.com/quick_start/pricing
Daily snapshot since May 2024 · 619 days captured
xAI
2026-10-18
https://x.ai/api
Daily snapshot since Nov 2024 · 537 days captured
Mistral
2026-10-18
https://mistral.ai/pricing
Daily snapshot since Dec 2023 · 678 days captured
Cohere
2026-10-18
https://cohere.com/pricing
Daily snapshot since Sep 2023 · 704 days captured

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 →