fix(ms-ai-architect): R5 G5b — 4 innholds-fikser (retired gpt-35-turbo→gpt-4o-mini, vector-quant GA 2024-07-01, 2 overclaims nyansert), hver live-verifisert per MS Learn-kilde [skip-docs]

This commit is contained in:
Kjell Tore Guttormsen 2026-07-04 17:09:23 +02:00
commit 36fd4cfe7b
5 changed files with 72 additions and 9 deletions

View file

@ -35,9 +35,9 @@ Denne referansen dekker regionvalg for Norge og EU, lastbalanseringsmonstre via
| Region | Primaer bruk | Modellstotte | Latens fra Norge | Datasuverenitet |
|--------|-------------|--------------|------------------|-----------------|
| Norway East | Primaer region | Begrenset (gpt-4o 2024-11-20) | < 10 ms | Norge/EU |
| Sweden Central | Sekundaer/failover | Bred (gpt-4o, o1, gpt-35-turbo) | ~15-25 ms | EU |
| West Europe | Alternativ | Begrenset (gpt-35-turbo) | ~30-40 ms | EU |
| UK South | Alternativ | Moderat (gpt-4o, gpt-35-turbo) | ~35-45 ms | UK (tilstrekkelig for mange bruksomrader) |
| Sweden Central | Sekundaer/failover | Bred (gpt-4o, o1, gpt-4o-mini) | ~15-25 ms | EU |
| West Europe | Alternativ | Begrenset (gpt-4o-mini) | ~30-40 ms | EU |
| UK South | Alternativ | Moderat (gpt-4o, gpt-4o-mini) | ~35-45 ms | UK (tilstrekkelig for mange bruksomrader) |
| France Central | Alternativ | Bred (gpt-4o, o1) | ~35-45 ms | EU |
### Anbefalte regionkombinasjoner
@ -295,11 +295,11 @@ Abonnement: DDT-AI-Prod
|
+-- Norway East
| +-- gpt-4o Data Zone: 120K TPM (primaer)
| +-- gpt-35-turbo: 60K TPM
| +-- gpt-4o-mini: 60K TPM
|
+-- Sweden Central
| +-- gpt-4o Data Zone: 120K TPM (sekundaer)
| +-- gpt-35-turbo: 120K TPM
| +-- gpt-4o-mini: 120K TPM
| +-- o1-mini Global Standard: 80K TPM
|
+-- France Central (failover)