open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 1 Activity
ms-ai-architect/skills/ms-ai-security/references/cost-optimization
History
Kjell Tore Guttormsen c1e5a22825 docs(ms-ai-architect): KB-refresh critical cost 5/8 — prompt-engineering verifisert mot prompt-caching + On Your Data-retirement 
Verifisert mot live Microsoft Learn (foundry/openai/how-to/prompt-caching,
foundry-classic/openai/concepts/use-your-data, ai-foundry/openai/concepts/model-retirements):
- Extended cache retention 24t BEKREFTET: «keeps cached prefixes active for longer, up to a maximum
  of 24 hours», param prompt_cache_retention='24h'. Model-gated: gpt-5/5.1/5.2/5.4 (+codex/chat) +
  gpt-4.1 (BEVISST utelatt gpt-5.5 — IKKE i extended-listen). Default 24h for nyere modeller
  (in_memory ikke støttet); gpt-5.4 og eldre: in_memory default. Filens «5-10 min/maks 1t» var kun
  in-memory-delen → cache-tabell splittet i in-memory vs extended + støttemodell-lister korrigert.
- On Your Data BEKREFTET deprecated, retires «October 14, 2026» → kilde #5 flagget m/ migrasjonspeker
  (Foundry Agent Service + Foundry IQ).
- prompt_cache_key-nyanse lagt til (~15 req/min overflow-grense, fra docs).

Korreksjons-disiplin (operatør-godkjent):
- Data-residens-nyanse (HØYVERDI for offentlig sektor): extended-cache holdes i-region KUN ved
  Regional Standard/Provisioned; Global/DataZone kan forlate region. Rettet GDPR- + Datasuverenitet-bullets
  (gammel «clears etter maks 1 time» + «lagres i samme region» var nå feil for extended).
- Pristabell: o1-preview (retired 2025-07) + GPT-4/32K (retired 2025-06) flagget retired m/ peker til
  kanonisk pricing (model-retirements-tabellen). Prompt Flow «GPT-3.5» → gjeldende modeller.
- Header 2026-02→2026-06, footer 2026-02-04→2026-06. 3 kilde-rader stemplet Verified MCP 2026-06. validate 239/0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 22:49:46 +02:00
..
ai-builder-credits-transition.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
azure-ai-foundry-cost-governance.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
azure-cost-management-ai.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
batch-processing-cost-reduction.md docs(ms-ai-architect): KB-refresh tema-a steg 1 — modellkatalog GPT-5.1→5.5 i 2 critical cost-filer 2026-06-23 20:34:45 +02:00
budget-forecasting-ai-projects.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
cost-allocation-chargeback.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
deterministic-cost-calculation-model.md fix(ms-ai-architect): re-baseline kostnadslaget (GPT-5 $1.25/$10, én prissannhet, 10 filer) 2026-06-18 12:45:21 +02:00
gpt5-gpt41-pricing-models.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
inference-endpoint-cost-optimization.md docs(ms-ai-architect): KB-refresh critical cost 4/8 — inference-endpoint verifisert mot Foundry priority-processing + deployment-types 2026-06-23 22:45:19 +02:00
licensing-compliance-cost-avoidance.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
model-selection-price-performance.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
multi-model-strategy-costs.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
observability-cost-reduction.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
prompt-engineering-cost-reduction.md docs(ms-ai-architect): KB-refresh critical cost 5/8 — prompt-engineering verifisert mot prompt-caching + On Your Data-retirement 2026-06-23 22:49:46 +02:00
ptu-vs-paygo-economics.md docs(ms-ai-architect): KB-refresh critical cost 1/8 — ptu-vs-paygo verifisert mot Foundry PTU-docs 2026-06-23 21:51:01 +02:00
rag-query-cost-reduction.md chore(ms-ai-architect): refresh KB critical-bucket — 15 files [skip-docs] 2026-06-19 06:22:48 +02:00
request-batching-aggregation.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
reserved-capacity-planning.md docs(ms-ai-architect): KB-refresh critical cost 2/8 — reserved-capacity verifisert mot Foundry reservations-docs 2026-06-23 22:24:56 +02:00
semantic-caching-patterns.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
small-language-models-economics.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
token-counting-optimization.md docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 2026-06-23 21:00:27 +02:00
vector-storage-cost-optimization.md chore(ms-ai-architect): refresh KB critical-bucket — 15 files [skip-docs] 2026-06-19 06:22:48 +02:00