LLMEOL CodeAP Studio

GPT-3.5 Turbo Deprecation, Shutdown Dates & Migration Guide

Runs locally in your browser — 0 bytes uploaded Synced 2026-11-12 UTC · 8 variants · 1 ecosystems

Track confirmed UTC deprecation and shutdown dates for GPT-3.5 Turbo (OpenAI) across OpenAI. Preview gpt-3.5-turbo-0125 → gpt-5.6-terra upgrades locally below, audit full configs in the Model Config Auditor, or benchmark token pricing in DevToken.

Tracked Variants 8
Earliest Upcoming EOL 2026-10-23
Recommended Upgrade gpt-5.6-terra
Ecosystems Covered OpenAI

1. Quick .env & SDK Snippet Replacement Matcher

Edit or paste your .env assignment, LiteLLM route, or SDK model identifier below to check live 3-state EOL status and copy a ready-to-apply replacement diff locally in your browser.

2 of 2 configured models need migration
Full .env Auditor → Compare gpt-5.6-terra Cost in DevToken →

Replacement Diff Preview (gpt-3.5-turbo-0125 → gpt-5.6-terra)

# OPENAI_MODEL: gpt-3.5-turbo-0125 -> gpt-5.6-terra [RETIRED · EOL 2026-10-23]
- OPENAI_MODEL="gpt-3.5-turbo-0125"
+ OPENAI_MODEL="gpt-5.6-terra"

# model: gpt-3.5-turbo-0125 -> gpt-5.6-terra [RETIRED · EOL 2026-10-23]
- model: openai/gpt-3.5-turbo-0125
+ model: openai/gpt-5.6-terra

2. Cross-Ecosystem GPT-3.5 Turbo Lifecycle Matrix (8)

Direct vendor APIs and cloud platforms retire dated snapshots on independent schedules. Verify the exact model ID, vendor lifecycle stage, and UTC shutdown date matching your deployment.

GPT-3.5 Turbo lifecycle status, UTC shutdown dates, and replacement models across OpenAI
Model ID Provider Calculated Status Confirmed Shutdown (UTC) Vendor Lifecycle Replacement & Migration Source
gpt-3.5-turbo OpenAI RETIRED 2026-10-2320d ago Retired
gpt-5.6-terra Cost → Audit →
Docs ↗
gpt-3.5-turbo-0125 OpenAI RETIRED 2026-10-2320d ago Retired
gpt-5.6-terra Cost → Audit →
Docs ↗
gpt-3.5-turbo-completions OpenAI RETIRED 2026-10-2320d ago Retired
gpt-5.6-terra Cost → Audit →
Docs ↗
gpt-3.5-turbo-1106 OpenAI RETIRED 2026-09-2845d ago Retired
gpt-5.6-terra Cost → Audit →
Docs ↗
gpt-3.5-turbo-instruct OpenAI RETIRED 2026-09-2845d ago Retired
gpt-5.6-terra Cost → Audit →
Docs ↗
gpt-3.5-turbo-0301 OpenAI RETIRED 2024-09-13790d ago Retired
gpt-3.5-turbo Cost → Audit →
Docs ↗
gpt-3.5-turbo-0613 OpenAI RETIRED 2024-09-13790d ago Retired
gpt-3.5-turbo Cost → Audit →
Docs ↗
gpt-3.5-turbo-16k-0613 OpenAI RETIRED 2024-09-13790d ago Retired
gpt-3.5-turbo Cost → Audit →
Docs ↗

3. Production Migration Checklist (gpt-3.5-turbo-0125 → gpt-5.6-terra)

Follow this deterministic engineering sequence before retiring pinned snapshots in production services and SDK clients:

  1. Inventory pinned model IDs: Search repositories and deployment manifests for OPENAI_MODEL, openai/ LiteLLM routes, and dated snapshot strings in the GPT-3.5 Turbo family (0 deprecated, 8 retired, 0 active variants tracked).
  2. Benchmark successor quality & token pricing: Validate structured output schemas, tool-calling payloads, and latency against gpt-5.6-terra, then compare input, output, and cached token rates in DevToken.
  3. Enforce keyless CI guardrails: Wire RSS, Atom, iCal feeds & CI Guard into pull-request checks so retired or deprecated GPT-3.5 Turbo identifiers cannot re-enter production.

Compare sibling model families or inspect full provider-level schedules across every ecosystem hosting this family:

5. GPT-3.5 Turbo Deprecation & Upgrade FAQ

Is GPT-3.5 Turbo deprecated or retired across OpenAI?

LLMEOL tracks 8 GPT-3.5 Turbo variants across OpenAI: 0 deprecated with scheduled shutdowns, 8 retired past their UTC EOL date, and 0 active with no announced shutdown date. Check the cross-ecosystem matrix above for exact snapshot dates.

What is the recommended replacement model when migrating off gpt-3.5-turbo-0125?

The primary recommended upgrade target for gpt-3.5-turbo-0125 is gpt-5.6-terra. Always test prompt formatting, max output tokens, and tool schemas on gpt-5.6-terra, and compare token pricing in DevToken before switching production traffic.

How can I replace gpt-3.5-turbo-0125 in .env and LiteLLM configs safely?

Paste your OPENAI_MODEL assignment or LiteLLM model block into the Quick Replacement Matcher on this page to generate an exact diff, or open the full Local Model Config Auditor to scan multi-service manifests with zero network upload.