- Azure OpenAI fine-tuning cheat sheet: training files, jobs, events, checkpoints, metrics and deploymentsAI & GenAI · 13 Nov 2026
- Reasoning models return 400 Unsupported parameter: fixing max_tokens, temperature and system messagesAI & GenAI · 13 Nov 2026
- Sharing one LLM tokens-per-minute quota across many app replicas: a Redis token bucket that counts tokens, not requestsAI & GenAI · 11 Nov 2026
- LLM API calls fail with CERTIFICATE_VERIFY_FAILED behind a corporate proxy: CA bundles and proxy settings for the OpenAI SDK, boto3 and Azure SDKsAI & GenAI · 10 Nov 2026
- Checklist: decommissioning a GenAI application - deployments, keys, indexes, logs and dataAI & GenAI · 8 Nov 2026
- LLM API calls hang for minutes: client timeouts, retries and connection limits in the OpenAI SDK and boto3AI & GenAI · 8 Nov 2026
- Azure OpenAI first call from Python: use Entra ID and get the deployment name rightAI & GenAI · 6 Nov 2026
- Azure OpenAI deployment creation fails: InsufficientQuota, model not available in region and policy denialsAI & GenAI · 3 Nov 2026
- LLM answers cut off mid-sentence: finish_reason length, max_tokens, reasoning tokens and context limitsAI & GenAI · 3 Nov 2026
- Load testing an LLM endpoint before go-live: TTFT, tokens per second, concurrency and where 429s startAI & GenAI · 31 Oct 2026
- Sev1: a batch or embedding job used up the LLM quota and production chat is getting 429sAI & GenAI · 31 Oct 2026
- Sev1: someone regenerated the Azure OpenAI keys and every app gets 401 — restore service and move to Entra IDAI & GenAI · 31 Oct 2026
- Token counts don't match the bill: why tiktoken estimates differ from the usage your LLM API reportsAI & GenAI · 31 Oct 2026
- Azure OpenAI batch jobs fail, stay in validating or never finish: input file errors, enqueued token quota and stuck jobsAI & GenAI · 30 Oct 2026
- LLM API basics: your first call, messages and roles, tokens, temperature and max tokensAI & GenAI · 29 Oct 2026
- Sev1: an LLM API key leaked to a public repo and someone is burning your quotaAI & GenAI · 29 Oct 2026
- Sev1: Azure OpenAI deployment deleted or renamed. Every call returns 404 DeploymentNotFoundAI & GenAI · 29 Oct 2026
- Azure OpenAI CLI cheat sheet: accounts, deployments, quota, keys, metrics and logsAI & GenAI · 27 Oct 2026
- Azure OpenAI o1, o3, o3-mini and o4-mini retire on 19 November 2026 - what auto-upgrades, what breaks, and how to migrate provisioned deploymentsAI & GenAI · 27 Oct 2026
- Lessons from the 29 September 2026 Azure OpenAI incident in Sweden Central - multi-region failover with API Management and sensible retriesAI & GenAI · 27 Oct 2026
- Microsoft Foundry model retirements, November-December 2026 - Claude, codex-mini, Llama 4 Maverick, gpt-4o, Mistral, whisper and ttsAI & GenAI · 27 Oct 2026
- Stop surprise model upgrades in Azure OpenAI - versionUpgradeOption, the Models API lifecycle fields and a weekly retirement reportAI & GenAI · 27 Oct 2026
- LLM API errors cheat sheet - what 400, 401, 403, 404, 408, 429, 500 and 503 mean on OpenAI, Azure OpenAI and BedrockAI & GenAI · 26 Oct 2026
- Prompt Shields and content safety for Azure OpenAI apps - setting up jailbreak and document attack detectionAI & GenAI · 26 Oct 2026
- A cost kill switch for GenAI: stopping runaway token spend automatically on Azure and AWSAI & GenAI · 25 Oct 2026
- A gateway kill switch for all LLM traffic: Azure API Management named values and policiesAI & GenAI · 25 Oct 2026
- Emergency cut-off for a model endpoint: blocking all access to Azure OpenAI or Bedrock in minutesAI & GenAI · 25 Oct 2026
- Optimization: getting value from provisioned throughput - PTU utilisation, spillover and right-sizingAI & GenAI · 25 Oct 2026
- Sev1: apps can't reach Azure OpenAI after a network change. Private endpoint DNS fixesAI & GenAI · 25 Oct 2026
- Sev1: LLM calls fail after a model version was retired or auto-upgradedAI & GenAI · 25 Oct 2026
- Transformation: migrating from the Assistants API to the Responses APIAI & GenAI · 25 Oct 2026
- Transformation: moving apps from the public OpenAI API to Azure OpenAI with enterprise controlsAI & GenAI · 25 Oct 2026
- Transformation: moving bulk LLM jobs from synchronous calls to batch inferenceAI & GenAI · 25 Oct 2026
- Runbook: rotate Azure OpenAI API keys without downtime, then switch apps to Entra IDAI & GenAI · 23 Oct 2026
- AI gateway foundation: one front door for every LLM call with Azure API ManagementAI & GenAI · 22 Oct 2026
- Azure OpenAI content filter errors: why legitimate prompts get blockedAI & GenAI · 22 Oct 2026
- Azure OpenAI deployment setup: Standard, Global, Data Zone and Provisioned (PTU) comparedAI & GenAI · 22 Oct 2026
- Highly available LLM endpoints: multi-region backend pools, priorities and circuit breakers in APIMAI & GenAI · 22 Oct 2026
- Runbook: model endpoint regional outage (Azure OpenAI, Bedrock, OCI GenAI)AI & GenAI · 22 Oct 2026
- Handling 429s and latency spikes from LLM APIsAI & GenAI · 19 Oct 2026