Blogg

Teknisk djupgående analys av AI, Azure, Next.js och beslutet bakom.

32 inlägg

OpenAI Decisions API lands in Foundry: Luna vs Decision-1

The OpenAI Decisions API went GA in Microsoft Foundry on 22 October 2026: GPT-6 Luna behind a dedicated endpoint at $0.10 per million input tokens, no output charge, images and 400 questions per call, available in Sweden Central. Azure teams now have two hosted decision models, and once a stable rubric is cached the Luna option lands within a few hundred dollars a month of Microsoft-Decision-1 at twenty million calls.

October 25, 2026165 visningarAzure & Cloud

One Google zone took down UK banks: your Azure zone audit

A power event in one Google Cloud zone, europe-west2-b in London, left Revolut, HSBC, Lloyds and the UK courts' video platform degraded for most of 20 October 2026, and regulators were asking questions within hours. Azure has the same three-zone model in Sweden Central and the same failure mode when resources are left nonzonal, so here is the service-by-service audit, the Sweden Central price of fixing it, and what DORA Articles 11 and 12 already demand.

October 21, 2026148 visningarAzure & Cloud

Claude OTel traces: the Azure Monitor path and Foundry gap

Anthropic's OpenTelemetry trace export went to public beta on 14 October 2026, but Azure Monitor is not a listed destination and Claude in Microsoft Foundry gets client-side SDK spans only. Three Azure paths (Collector on Container Apps, Microsoft OpenTelemetry Distro with managed identity, Agent SDK signals), the Entra-versus-static-header mismatch that forces the design, and the Application Insights cost math for full-content mode.

October 16, 2026187 visningarAzure & Cloud

Azure OpenAI On Your Data is retired: your Foundry IQ path

Azure OpenAI On Your Data retired on 14 October 2026, and Microsoft says the replacement paths are not feature-equivalent: a Foundry IQ knowledge base on Azure AI Search, called directly or through Foundry Agent Service. The guide covers how to find affected data_sources calls, the GA-versus-preview API decision, the parameter mapping, the stricter per-user authorization model, the two-bill cost math, and Sweden Central capacity.

October 15, 2026219 visningarAzure & Cloud

Azure Maia 300: what Microsoft silicon means for Foundry

Microsoft announced Azure Maia 300 on 12 October 2026 with 288 GB of HBM4, 18 TB/s and a claim of 40% more tokens per megawatt, but the chip that reaches Microsoft Foundry by year end is Maia 200, serving OpenAI and open-weight models in unnamed European regions with no price change. What the silicon transition does and does not change for EU data zone deployments, model choice and your evaluation baseline.

October 13, 2026236 visningarAzure & Cloud

Microsoft-Decision-1 in Foundry: $0.042 and the EU zone

Microsoft-Decision-1 went GA in Microsoft Foundry on 9 October 2026 at $0.042 per million input tokens with free output, returning calibrated probabilities over fixed options instead of text, and it launched with an EU Data Zone at the same price as the US zone. We compare it with OpenAI's Decisions API and H2O-Lightning-4B, run the cost math for ticket routing and agent step-gating, and set out what Swedish buyers must record about its Qwen3.5-9B base.

October 10, 2026347 visningarAzure & Cloud

Claude Haiku 5.5 in Foundry: $0.10 and the 100K cliff

Claude Haiku 5.5 is GA in Microsoft Foundry at $0.10/$0.50 per million tokens, the same Global Standard list price as GPT-6 Luna, and 90% below Haiku 4.5 on paper. The bills diverge on three lines: a tier that charges 5x on every token once a prompt passes 100K, a tokenizer that counts the same text as 30% more tokens, and an EU Data Zone that Luna offers at $0.12/$0.60 while Claude on Foundry has none.

October 8, 2026249 visningarAzure & Cloud

Sonnet 5.5 vs GPT-6.1 Sol on Azure: the $2/$10 cost math

Claude Sonnet 5.5 and GPT-6.1 Sol reached Microsoft Foundry a day apart at the same $2/$10 list price, yet a cache-heavy 60-turn agent session costs $3.45 on Sonnet 5.5 and $2.55 on GPT-6.1 Sol, or $3.06 in the EU Data Zone that Claude still lacks. Above 272K input tokens the order flips, because GPT-6.1 Sol doubles its input rate while Sonnet 5.5 keeps flat pricing to 1M tokens and can run with no up-front reasoning.

September 30, 2026443 visningarAzure & Cloud

Claude Opus 5.5 in Foundry: the Opus 5 migration cost math

Claude Opus 5.5 is GA in Microsoft Foundry at $4/$20 per million tokens with cache reads at $0.20, which cuts a cache-heavy 60-turn agent session from $8.63 on Opus 5 to $5.10 and brings it within 1.5x of Sonnet 5. The saving can reverse on uncached endpoints that ran Opus 5 with thinking disabled, because thinking is now always on, the default effort dropped to medium, and Foundry still offers no EU data zone, batch pricing or fast mode.

September 24, 2026699 visningarAzure & Cloud

Azure's 30 September retirements: what stops working

More than ten Azure items retire on 30 September 2026, and the ones that fail silently are more dangerous than the ones that fail loudly: URL ping tests are deleted from your resources and the ContainerLog table stops receiving data, taking alert rules down with them. A triage guide with Resource Graph queries, Sweden Central cost math for standard web tests and Basic Logs, and a checklist for the Functions v3, Service Bus SBMP and 1 October AI service deadlines.

September 19, 20261 038 visningarAzure & Cloud

AWS lost Bahrain for good: your Azure region-loss plan

AWS confirmed on 15 September 2026 that data hosted only in its Bahrain region, and in one UAE Availability Zone, is permanently lost after Iranian strikes damaged multiple zones, proving that multi-AZ design protects availability but not against losing a whole region. For Azure teams in Sweden and the EU, the fix is a classified inventory, GZRS and geo-redundant backups for critical data, and early access to restricted pair regions such as Sweden South.

September 17, 2026495 visningarAzure & Cloud

GPT-6 Astra migration on Azure: the GPT-5.6 Sol checklist

GPT-5.6 Sol retires on Foundry in January 2028, so moving to GPT-6 Astra is a choice rather than a deadline, and it touches more than a deployment name: tool calls must move to the Responses API, effort none and temperature disappear, and every line on the price sheet costs 2 to 2.5 times more. A phase-by-phase checklist built on Microsoft's migration process, OpenAI's model guidance and the Learn pages, with the Swedish residency caveat that keeps part of your traffic on Sol.

September 11, 2026756 visningarAzure & Cloud