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 tracked models

AWS Bedrock model lifecycle and end-of-life dates

Bedrock moves a model through legacy and then end-of-life, and the schedule varies by the model's original vendor because Bedrock hosts models from several. A Bedrock migration frequently crosses vendors, which means the request and response shapes change, not only the model id.

We track 23 AWS Bedrock models, 23 of them with a published retirement date. 11 need attention now.

Retiring or deprecated now

Deprecated models still answer but are superseded. Anything inside the 90-day window has a date attached and will stop answering on it.

AWS Bedrock models that are deprecated or retiring soon
ModelStateRetirementReplacement
cohere.command-r-v1:0retiring2026-08-19 · past due—
anthropic.claude-3-haiku-20240307-v1:0retiring2026-09-10 · past due—
amazon.nova-premier-v1:0retiring2026-09-14 · past due—
amazon.nova-sonic-v1:0retiring2026-09-14 · past due—
amazon.nova-canvas-v1:0retiring2026-09-30 · in 12 days—
amazon.nova-reel-v1:0retiring2026-09-30 · in 12 days—
amazon.nova-reel-v1:1retiring2026-09-30 · in 12 days—
anthropic.claude-sonnet-4-20250514-v1:0retiring2026-10-14 · in 26 days—
ai21.jamba-1-5-large-v1:0deprecated2026-11-26 · in 69 days—
ai21.jamba-1-5-mini-v1:0deprecated2026-11-26 · in 69 days—
twelvelabs.marengo-embed-2-7-v1:0deprecated2026-11-30 · in 73 days—

Already retired

These ids no longer answer. If one appears in your code or in something an assistant wrote for you, it is already broken.

AWS Bedrock models that are already retired
ModelStateRetirementReplacement
amazon.titan-image-generator-v2:0retired2026-06-30 · retired—
meta.llama3-1-405b-instruct-v1:0retired2026-07-07 · retired—
meta.llama3-2-11b-instruct-v1:0retired2026-07-07 · retired—
meta.llama3-2-1b-instruct-v1:0retired2026-07-07 · retired—
meta.llama3-2-3b-instruct-v1:0retired2026-07-07 · retired—
meta.llama3-2-90b-instruct-v1:0retired2026-07-07 · retired—
anthropic.claude-3-5-sonnet-20240620-v1:0retired2026-07-30 · retired—
anthropic.claude-3-5-sonnet-20241022-v2:0retired2026-07-30 · retired—
anthropic.claude-3-7-sonnet-20250219-v1:0retired2026-07-30 · retired—
anthropic.claude-3-sonnet-20240229-v1:0retired2026-07-30 · retired—
cohere.command-r-plus-v1:0retired2026-08-19 · retired—

Currently safe

Active, announced, or legacy with no imminent date. Legacy models are superseded but still served.

AWS Bedrock models with no imminent retirement
ModelStateRetirementReplacement
anthropic.claude-opus-4-1-20250805-v1:0legacy2027-01-08 · in 112 days—

Find out which of these you are paying for

A list of dates only helps once you know which of these models your own traffic hits. One line of code meters the models your app actually calls, then reports the monthly spend sitting on each retiring id and what the move to its replacement costs.

See it on sample trafficStart free

Other providers

Azure OpenAIOpenAIAnthropic ClaudeGoogle Gemini and Vertex AICohere

Source: AWS — Bedrock model lifecycle. Every record links the page it was parsed from and keeps AWS Bedrock’s own wording, so a normalization decision stays checkable.

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.