ms-ai-architect/skills/ms-ai-security/references/cost-optimization
Kjell Tore Guttormsen 692b3f75d8 docs(ms-ai-architect): KB-refresh critical cost 6/8 — token-counting verifisert mot fine-tuning-cost (RFT) + prompt-caching
Verifisert mot live Microsoft Learn (foundry/openai/how-to/fine-tuning-cost-management,
prompt-caching, use-your-data):
- RFT (Reinforcement Fine-Tuning) lagt til (filen dekket kun SFT/DPO): tidsbasert «pris = treningstid
  × timepris + grader-tokens», ~$100/time core training for o4-mini-2025-04-16, per-job-tak $5000
  (pauses + deploybart checkpoint ved tak, kan resume uten videre pristak). Cost-control-strategier med.
- Cache-TTL-tabell hadde FEIL akse («Foundry Classic vs AI Services») → korrigert til in-memory
  (5-10 min/maks 1t, alle GPT-4o+) vs extended (24h, GPT-5-serien+gpt-4.1, default for nyere).
- prompt_cache_key ~15 req/min overflow-caveat lagt til.
- On Your Data deprecation 2026-10-14 flagget (3 steder: token-est-seksjon, Foundry-seksjon, kilde #6).
- tiktoken model-set manglet o1-mini/o3-mini → lagt til.
- Header 2026-02→2026-06, verification-date 2026-02-04→2026-06. Priser urørt (kanonisk peker). validate 239/0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 22:53:35 +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 critical cost 6/8 — token-counting verifisert mot fine-tuning-cost (RFT) + prompt-caching 2026-06-23 22:53:35 +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