Part of the AWS re:Invent 2026 attendee blog series - start at the index for venue map, transit times, Expo strategy and the persona matrix.
Who it's for: FinOps practitioners, CFOs and finance partners, platform and architecture leads, product owners who carry an AI P&L, and engineering leaders who are asked to prove ROI. Topics are token and inference costs, model selection, distillation, caching and batch, FinOps for generative AI, agent unit economics, and measuring AI productivity gains. Cost content is split between MGM Grand and Wynn, with key chalk talks at Caesars Palace. All sessions come from the official catalog (read Nov 12, 2026).
Career tracks
- Early career: COP209, ARC204, COP348, PEX210.
- Mid career: AIM3311, COP311-R, IND307-R, AIM319, COP328-R1.
- Senior / budget owners: AIM437-R, AIM448, OPN406-R1, DAT421, PEX303-R1, AIM409-R.
Must-attend keynotes: CEO Keynote – Matt Garman (8:30 AM, The Venetian) (pricing and platform news) and Technology Innovation Keynote (8:30 AM, The Venetian).
What to see
New launches
- COP209 covers AWS FinOps enhancements on both sides: AI for FinOps, and FinOps for AI.
- COP311-R (repeats COP311-R1) is a builders' session on the latest cost-management capabilities for Amazon Bedrock.
- AIM220 (what's new in Amazon Bedrock) explicitly covers "new economics".
- The embargoed "[NEW LAUNCH]" AI slots are listed in the AI architectures post .
Keynote announcements will add sessions during the event, so this list will grow. Check the catalog's new-launch filter after each keynote and every evening, and search the catalog for "[NEW LAUNCH]".
Established products
- Token and inference cost: AIM437-R (route, cache and batch), AIM448 (choosing an inference strategy), OPN406-R1 (context-efficient agents), DAT421 (KV cache), DAT435 (semantic caching) and AIM409-R (prompt caching, Intelligent Prompt Routing and right-sizing).
- Model selection and distillation: AIM438-R, AIM361 (customizing open-weight models), CMP327-R1 (token economics across AWS silicon) and AIM3301.
- Agent cost control: AIM3310-R1, AIM3321, COM312-R1 (giving your agent a wallet) and ARC204.
- FinOps for generative AI and Cloud Financial Management: AIM3311, COP328-R1, COP329-R, COP324-R, COP403-R, COP348 and IND3306 (Ramp tracks AI spend down to the API key).
- ROI, profitability and productivity gains: AIM319 (token counts to business impact), IND307-R (LLM tokenomics), PEX303-R1 (unit economics of production agents), PEX205 (AI-powered profitability), PEX210 and PEX217 (selling to AI agents).
AI security
Security and governance have a cost too. Guardrail and evaluation calls add tokens, keys and logs add line items, and every control adds some latency, so price them against the risk they remove. SEC435 shows the other side of the ledger: AWS threat researchers on the tokenomics that make AI-powered attacks cheap. SEC308-R builds a KMS key-lifecycle dashboard with usage and cost insights, and COP328-R1 and COM312-R1 fold governance into cost control. SEC435 and SEC308-R are now in the plan below. The rest of the AI-security track is in the AI security post .
Fixed points of the week (official agenda, PT): Expo Welcome Reception Mon 4–7 PM · Expo Tue–Wed 10 AM–6 PM, Expo Happy Hour Wed 4:30–6 PM, Thu 10 AM–4 PM (last chance for swag) · networking receptions Tue 6–8 PM (Caesars Palace, Venetian) and Wed 6–8 PM (Caesars Palace, Venetian, Wynn|Encore) · AMPED Industries & Startup Party Wed 7 PM at AREA15 (RSVP) · re:Play Thu 6:30–10:30 PM at Allegiant Stadium (shuttles from 6:15 PM) · Friday is a half day (limited service at Venetian and Wynn|Encore until ~1 PM). Breakfast and lunch are served on full conference days — eat at the venue of your next session.
Day-by-day (clustered by venue)
Monday Nov 30 — pick a lane: South or North
- South · MGM Grand: AIM438-R Switch models in production without disrupting customers on Amazon Bedrock (9:00 AM, MGM Grand), then AIM437-R Route, cache, and batch: a multi-model decision framework on Bedrock (10:00 AM, MGM Grand), then ARC302-R Building multi-tenant RAG: Isolation, cost, and scale (11:30 AM, MGM Grand). After lunch, take the AIM409-R Build a cost optimization playbook for your AI workload (2:30 PM, MGM Grand) builders' session (reserve a seat) or AIM361 Customize open-weight models for accuracy, cost, and latency on SageMaker AI (2:30 PM, MGM Grand) (same slot), then AIM319 Token Counts to Business Impact: Measurable AI Architectures at Scale (4:00 PM, MGM Grand).
- North · Wynn: the COP324-R AI-Powered FinOps: Cloud Cost Optimization in Practice (8:30 AM, Wynn/Encore) workshop (AI-powered FinOps), then SEC308-R Build a KMS key lifecycle dashboard with usage and cost insights (10:30 AM, Wynn/Encore) (KMS key costs), then COP403-R Optimize AI apps on Amazon Bedrock for cost, latency, and control (11:30 AM, Wynn/Encore), then ARC204 Architectural patterns for predictable multi-agent costs at scale (1:30 PM, Wynn/Encore), then IND307-R Mastering LLM tokenomics: From token costs to business outcomes (3:00 PM, Wynn/Encore).
- 🌙 From Wynn it is a 10–15 min walk, and from MGM Grand a 30+ min shuttle, to the Venetian for COP348 Monitor and optimize costs for Amazon Bedrock (5:30 PM, The Venetian) and Expo Welcome Reception (4:00 PM, The Venetian). South-lane attendees may miss COP348; go straight to the Expo. Then Developer Keynote (7:30 PM, The Venetian) if you like.
Tuesday Dec 1 — keynote, then MGM Grand
- AM · Venetian: CEO Keynote – Matt Garman (8:30 AM, The Venetian), then take the shuttle 30+ min to MGM Grand and eat lunch there.
- PM · MGM Grand: AIM3311 See where every AI dollar goes on Amazon Bedrock (12:00 PM, MGM Grand), then at 2:30 pick COP209 Manage cloud costs and AI spend with AWS Cost Management (2:30 PM, MGM Grand) (early or mid career) or OPN406-R1 Cut token costs by 50%: Building context efficient agents with Strands (2:30 PM, MGM Grand) (senior). Then pick DAT435 Implement semantic caching for AI agents using ElastiCache for Valkey (4:30 PM, MGM Grand) or AIM3301 Make every GPU count: Maximizing GPU efficiency for inference at scale (4:30 PM, MGM Grand) (same slot).
- 🌙 Networking receptions (Caesars Palace & The Venetian) (6:00 PM, The Venetian or Caesars Palace) (from MGM Grand, Caesars Palace is the closest reception; 20–25 min by shuttle). Unofficial: FinOps After Dark by Finout (Tue 6–9 PM, Rockhouse, Venetian). (Unofficial, invite-only listing from conferenceparties.com. Request an invite, and confirm the time and location with the host.)
Wednesday Dec 2 — Center morning, South afternoon
- AM · Caesars Palace (skip the Data & AI keynote and watch the replay): PEX303-R1 Govern, Bill, and Attribute: The Unit Economics of Production Agents (10:00 AM, Caesars Palace), then walk 5–10 min to Caesars Forum for an early lunch.
- Midday · Caesars Forum: DAT421 Reduce LLM inference cost with Amazon ElastiCache for Valkey (12:00 PM, Caesars Forum).
- PM · MGM Grand (20–25 min by shuttle): AIM448 Build the right inference strategy on Amazon Bedrock (3:00 PM, MGM Grand), then COP328-R1 Building a Cost Governance framework for AI that scales (4:30 PM, MGM Grand). Hands-on alternative: the COP324-R1 AI-Powered FinOps: Cloud Cost Optimization in Practice (3:30 PM, MGM Grand) workshop.
- 🌙 AMPED: Industries & Startup Party (RSVP in portal) (7:00 PM, AREA15) or Networking receptions (Caesars Palace, The Venetian, Wynn|Encore) (6:00 PM, The Venetian or Caesars Palace / Wynn|Encore) (Caesars Palace is the closest reception to MGM Grand).
Thursday Dec 3 — keynote, Wynn, then Caesars Palace
- AM · Venetian: Technology Innovation Keynote (8:30 AM, The Venetian), then walk 10–15 min to Wynn.
- Late AM · Wynn: the COP311-R FinOps for AI: Cost allocation strategies for Amazon Bedrock (10:30 AM, Wynn/Encore) builders' session, or SEC435 Tokenomics of attacks: how AWS defends you from AI-powered threats (10:30 AM, Wynn/Encore) (same slot) for the attacker's side of AI economics.
- Midday · Caesars Palace (20–25 min walk): AIM3310-R1 Stop the bleed: control and optimize agent costs on AgentCore (12:00 PM, Caesars Palace).
- PM · Caesars Palace: CMP327-R1 Optimize AI value: Compare token economics on AWS silicon (1:30 PM, Caesars Palace), then COM312-R1 Giving Your AI Agent a Wallet: The Architecture of Spend Control (2:30 PM, Caesars Palace) or IND307-R1 Mastering LLM tokenomics: From token costs to business outcomes (3:00 PM, Caesars Palace) (they overlap; pick one).
- South alternative: AIM3321 Control and optimize the cost of agents on Amazon Bedrock AgentCore (11:30 AM, MGM Grand), then COP328-R Building a Cost Governance framework for AI that scales (1:00 PM, MGM Grand), both at MGM Grand.
- The Expo closes at 4 PM. 🌙 re:Play (6:30 PM, Allegiant Stadium).
Friday Dec 4 — light, Venetian only
- PEX217 Sell to AI agents through AWS Marketplace (9:00 AM, The Venetian), then catch up on keynote and session recordings. As of Nov 12 the catalog lists no other AI-cost session on Friday.
Transit rules of thumb (estimates): Venetian↔Wynn/Encore 10–15 min walk · Venetian↔Caesars Forum 15–20 min · Caesars Forum↔Caesars Palace 5–10 min (0.4 mi — they are different buildings) · Center↔MGM Grand ~20–25 min by shuttle · North↔MGM Grand 30+ min by shuttle. Shuttles run ~6 AM to early evening (check the AWS Events app for live times).
Session table
Code | Title | Type / Level | Day / Time (PT) | Venue | Add to agenda | | |
|---|---|---|---|---|---|---|---|
COP324-R | AI-Powered FinOps: Cloud Cost Optimization in Practice | Workshop 300 | Mon Nov 30 · 8:30 AM–10:30 AM | Wynn/Encore · Cristal 7 | Catalog ★ | | |
AIM438-R | Switch models in production without disrupting customers on Amazon Bedrock | Chalk talk 400 | Mon Nov 30 · 9:00 AM–10:00 AM | MGM Grand · Boulevard 162 | Catalog ★ | | |
AIM437-R | Route, cache, and batch: a multi-model decision framework on Bedrock | Chalk talk 400 | Mon Nov 30 · 10:00 AM–11:00 AM | MGM Grand · Premier 320 | Catalog ★ | | |
SEC308-R | Build a KMS key lifecycle dashboard with usage and cost insights | Builders' session 300 | Mon Nov 30 · 10:30 AM–11:30 AM | Wynn/Encore · Latour 7 | Catalog ★ | | |
ARC302-R | Building multi-tenant RAG: Isolation, cost, and scale | Chalk talk 300 | Mon Nov 30 · 11:30 AM–12:30 PM | MGM Grand · Premier 311 | Catalog ★ | | |
COP403-R | Optimize AI apps on Amazon Bedrock for cost, latency, and control | Code talk 400 | Mon Nov 30 · 11:30 AM–12:30 PM | Wynn/Encore · Cristal 2, Content Hub, Code Talk | Catalog ★ | | |
ARC204 | Architectural patterns for predictable multi-agent costs at scale | Chalk talk 200 | Mon Nov 30 · 1:30 PM–2:30 PM | Wynn/Encore · La Tache 2 | Catalog ★ | | |
AIM361 | Customize open-weight models for accuracy, cost, and latency on SageMaker AI | Breakout 300 | Mon Nov 30 · 2:30 PM–3:30 PM | MGM Grand · Chairman's 363, Content Hub, Red Theater | Catalog ★ | | |
AIM409-R | Build a cost optimization playbook for your AI workload | Builders' session 400 | Mon Nov 30 · 2:30 PM–3:30 PM | MGM Grand · Chairman's 363, Content Hub, Builders' Session 2 | Catalog ★ | | |
IND307-R | Mastering LLM tokenomics: From token costs to business outcomes | Chalk talk 300 | Mon Nov 30 · 3:00 PM–4:00 PM | Wynn/Encore · Chopin 4 | Catalog ★ | | |
AIM319 | Token Counts to Business Impact: Measurable AI Architectures at Scale | Breakout 300 | Mon Nov 30 · 4:00 PM–5:00 PM | MGM Grand · Chairman's 363, Content Hub, Red Theater | Catalog ★ | | |
EXPO-WELCOME | Expo Welcome Reception | Event | Mon Nov 30 · 4:00 PM–7:00 PM | The Venetian · Hall B, Expo | Catalog ★ | | |
PEX210 | Delivering Measurable Customer Business Outcomes | Lightning talk 200 | Mon Nov 30 · 4:30 PM–4:50 PM | The Venetian · Hall B, Expo, Partner Advantage Theater | Catalog ★ | | |
COP348 | Monitor and optimize costs for Amazon Bedrock | Lightning talk 300 | Mon Nov 30 · 5:30 PM–5:50 PM | The Venetian · Hall B, Expo, Global Impact Theater | Catalog ★ | | |
KEY-DEV | Developer Keynote | Keynote | Mon Nov 30 · 7:30 PM–8:45 PM | The Venetian · Ballroom E, Keynote | Catalog ★ | | |
KEY-CEO | CEO Keynote – Matt Garman | Keynote | Tue Dec 1 · 8:30 AM–10:30 AM | The Venetian · Ballroom E, Keynote | Catalog ★ | | |
AIM3311 | See where every AI dollar goes on Amazon Bedrock | Code talk 300 | Tue Dec 1 · 12:00 PM–1:00 PM | MGM Grand · Chairman's 363, Content Hub, Code Talk | Catalog ★ | | |
COP209 | Manage cloud costs and AI spend with AWS Cost Management | Breakout 200 | Tue Dec 1 · 2:30 PM–3:30 PM | MGM Grand · Premier 318 | Catalog ★ | | |
OPN406-R1 | Cut token costs by 50%: Building context efficient agents with Strands | Code talk 400 | Tue Dec 1 · 2:30 PM–3:30 PM | MGM Grand · Boulevard 159 | Catalog ★ | | |
AIM3301 | Make every GPU count: Maximizing GPU efficiency for inference at scale | Breakout 300 | Tue Dec 1 · 4:30 PM–5:30 PM | MGM Grand · Chairman's 363, Content Hub, Blue Theater | Catalog ★ | | |
DAT435 | Implement semantic caching for AI agents using ElastiCache for Valkey | Builders' session 400 | Tue Dec 1 · 4:30 PM–5:30 PM | MGM Grand · Chairman's 363, Content Hub, Builders' Session 1 | Catalog ★ | | |
RECEPT-TUE | Networking receptions (Caesars Palace & The Venetian) | Event | Tue Dec 1 · 6:00 PM–8:00 PM | The Venetian or Caesars Palace | Catalog ★ | | |
PEX303-R1 | Govern, Bill, and Attribute: The Unit Economics of Production Agents | Chalk talk 300 | Wed Dec 2 · 10:00 AM–11:00 AM | Caesars Palace · Octavius 11 | Catalog ★ | | |
DAT421 | Reduce LLM inference cost with Amazon ElastiCache for Valkey | Breakout 400 | Wed Dec 2 · 12:00 PM–1:00 PM | Caesars Forum · Forum 120, Content Hub, Light Blue Theater | Catalog ★ | | |
IND3306 | How Ramp tracks and governs AI spend down to the team, model, and API key | Breakout 300 | Wed Dec 2 · 1:30 PM–2:30 PM | Wynn/Encore · Cristal 2, Content Hub, Purple Theater | Catalog ★ | | |
AIM448 | Build the right inference strategy on Amazon Bedrock | Breakout 400 | Wed Dec 2 · 3:00 PM–4:00 PM | MGM Grand · Chairman's 363, Content Hub, Blue Theater | Catalog ★ | | |
COP324-R1 | AI-Powered FinOps: Cloud Cost Optimization in Practice | Workshop 300 | Wed Dec 2 · 3:30 PM–5:30 PM | MGM Grand · Grand 124 | Catalog ★ | | |
COP311-R1 | FinOps for AI: Cost allocation strategies for Amazon Bedrock | Builders' session 300 | Wed Dec 2 · 4:30 PM–5:30 PM | Wynn/Encore · Latour 7 | Catalog ★ | | |
COP328-R1 | Building a Cost Governance framework for AI that scales | Chalk talk 300 | Wed Dec 2 · 4:30 PM–5:30 PM | MGM Grand · Boulevard 165 | Catalog ★ | | |
RECEPT-WED | Networking receptions (Caesars Palace, The Venetian, Wynn | Encore) | Event | Wed Dec 2 · 6:00 PM–8:00 PM | The Venetian or Caesars Palace / Wynn | Encore | Catalog ★ |
AMPED | AMPED: Industries & Startup Party (RSVP in portal) (end time not published; RSVP required) | Event | Wed Dec 2 · 7:00 PM | AREA15 | Catalog ★ | | |
AIM220 | What's new in Amazon Bedrock | Breakout 200 | Thu Dec 3 · 8:30 AM–9:30 AM | MGM Grand · Premier 318 | Catalog ★ | | |
KEY-TECH | Technology Innovation Keynote | Keynote | Thu Dec 3 · 8:30 AM–10:00 AM | The Venetian · Ballroom E, Keynote | Catalog ★ | | |
COP311-R | FinOps for AI: Cost allocation strategies for Amazon Bedrock | Builders' session 300 | Thu Dec 3 · 10:30 AM–11:30 AM | Wynn/Encore · Latour 7 | Catalog ★ | | |
PEX205 | AI-Powered Profitability: How Partners Are Winning with AWS | Breakout 200 | Thu Dec 3 · 10:30 AM–11:30 AM | Caesars Palace · Roman I | Catalog ★ | | |
SEC435 | Tokenomics of attacks: how AWS defends you from AI-powered threats | Chalk talk 400 | Thu Dec 3 · 10:30 AM–11:30 AM | Wynn/Encore · Fleurie | Catalog ★ | | |
AIM3321 | Control and optimize the cost of agents on Amazon Bedrock AgentCore | Breakout 300 | Thu Dec 3 · 11:30 AM–12:30 PM | MGM Grand · Grand 117 | Catalog ★ | | |
AIM3310-R1 | Stop the bleed: control and optimize agent costs on AgentCore | Chalk talk 300 | Thu Dec 3 · 12:00 PM–1:00 PM | Caesars Palace · Octavius 14 | Catalog ★ | | |
COP329-R | Automate savings with AWS Billing and Cost Management services | Chalk talk 300 | Thu Dec 3 · 12:00 PM–1:00 PM | Wynn/Encore · La Tache 2 | Catalog ★ | | |
COP328-R | Building a Cost Governance framework for AI that scales | Chalk talk 300 | Thu Dec 3 · 1:00 PM–2:00 PM | MGM Grand · Premier 311 | Catalog ★ | | |
CMP327-R1 | Optimize AI value: Compare token economics on AWS silicon | Chalk talk 300 | Thu Dec 3 · 1:30 PM–2:30 PM | Caesars Palace · Octavius 9 | Catalog ★ | | |
COM312-R1 | Giving Your AI Agent a Wallet: The Architecture of Spend Control | Chalk talk 300 | Thu Dec 3 · 2:30 PM–3:30 PM | Caesars Palace · Octavius 11 | Catalog ★ | | |
IND307-R1 | Mastering LLM tokenomics: From token costs to business outcomes | Chalk talk 300 | Thu Dec 3 · 3:00 PM–4:00 PM | Caesars Palace · Octavius 9 | Catalog ★ | | |
REPLAY | re:Play | Event | Thu Dec 3 · 6:30 PM–10:30 PM | Allegiant Stadium | Catalog ★ | | |
PEX217 | Sell to AI agents through AWS Marketplace | Breakout 200 | Fri Dec 4 · 9:00 AM–10:00 AM | The Venetian · Ballroom F, Content Hub, Blue Theater | Catalog ★ | | |
* = estimated end time · Keynotes and breakouts are walk-up, so arrive 15 minutes early · Confirm rooms in the AWS Events app.
Enjoyed reading this content? Let the author know!
Your likes, comments, shares, and saves help creators reach more builders.
Loading recommendations
Loading article