LLMIntel
OverviewLive demoCatalogCompareMCPPricingChangelogDocs
Start free
LLMIntel

A verified, normalized feed of AI model lifecycle events across every major provider, so a deprecation shows up on your roadmap instead of in your error logs. Plus runtime telemetry for what those models actually cost you.

Questions? support@llmintel.ai

Product
  • Pricing
  • Compare models
  • Azure OpenAI retirements
  • Dashboard
  • Changelog
  • Contact support
Developers
  • Quickstart
  • Model catalog
  • What’s retiring
  • MCP server
  • API reference
  • OpenAPI spec
  • Lifecycle RSS feed
  • @llmintel/telemetry
Free & open data

The model catalog is a normalized, machine-readable source of truth for AI model lifecycle events. It is free via the public API, and every record links to the primary provider source it came from.

© 2026 Alex Tsimbalistov. All rights reserved.
LLMIntel
OverviewLive demoCatalogCompareMCPPricingChangelogDocs
Start free
← All deadlines

gpt-4o-transcribe-diarize (2025-10-15) retires Apr 15, 2027

This model retires in 177 days. After 2027-04-15, API calls to this ID will fail.

Azure AI Foundry (1)

ModelStatusReplacementInput ΔOutput Δ
gpt-4o-transcribe-diarize (2025-10-15)retiring———

View all Azure AI Foundry models →

Migration checklist

  • Find all usages: Search your codebase for the retiring model IDs (grep, IDE search, or git grep "model-id").
  • Check dependencies: Review dependencies that might call these models indirectly (libraries, SDKs, agent frameworks).
  • Update configurations: Change model IDs in config files, environment variables, and API calls to the recommended replacements.
  • Test thoroughly: Verify output quality and latency with the new model on representative inputs before deploying.
  • Monitor spend: Track cost changes after migration. Use LLMIntel telemetry to measure actual per-model costs.

Get notified when this changes

We'll email you when any of these models change status or when new retirement dates are announced. Free, no account needed.

Track your own spend

This page shows what's retiring. It doesn't show which of these you call, or what the forced switch costs on your actual traffic. One line of code meters every model your app uses, then puts a dollar figure on each migration.

See it on sample trafficStart free

Related

All deadlinesAll retiring modelsLifecycle changelogMCP server
LLMIntel

A verified, normalized feed of AI model lifecycle events across every major provider, so a deprecation shows up on your roadmap instead of in your error logs. Plus runtime telemetry for what those models actually cost you.

Questions? support@llmintel.ai

Product
  • Pricing
  • Compare models
  • Azure OpenAI retirements
  • Dashboard
  • Changelog
  • Contact support
Developers
  • Quickstart
  • Model catalog
  • What’s retiring
  • MCP server
  • API reference
  • OpenAPI spec
  • Lifecycle RSS feed
  • @llmintel/telemetry
Free & open data

The model catalog is a normalized, machine-readable source of truth for AI model lifecycle events. It is free via the public API, and every record links to the primary provider source it came from.

© 2026 Alex Tsimbalistov. All rights reserved.