Topic
Model lifecycle tracker — deprecations, retirements and migrations
Which models are being deprecated or retired, when the cutoff lands, what replaces them, and how to move traffic without a rewrite.
Why this page exists
Providers retire models on their own schedule, and the notice usually lands in a changelog you were not watching. The practical question is never “is it deprecated” — it is which model takes over, what changes in the request, and whether anything can absorb the switch while you test. Each entry below covers a specific event; the routing layer is what lets you move without a rewrite.
September 2026
- GuideQ4 2026 AI Model Deprecation Calendar: Every Sunset Date Across OpenAI, DashScope, Anthropic, and GoogleOctober through December 2026 brings the year's largest wave of AI model retirements. OpenAI removes GPT-3.5 Turbo, GPT-4, o1, o3-mini, and o4-mini in a single October 23 sweep. DashScope sunsets dozens of legacy models on October 10. Anthropic's earliest active floors start expiring. This is the unified cross-provider calendar with every date, replacement model, and routing fallback config.
- GuideOpenAI October 2026 Model Deprecation Planning Guide: GPT-5.4-Cyber, GPT-3.5, GPT-4, and O1 Shutdown TimelineOpenAI shuts down gpt-5.4-cyber on October 1 and retires gpt-3.5-turbo, gpt-4, gpt-4-turbo, and o1 snapshots on October 23, 2026. This migration guide covers every affected model, the replacement mapping, code diffs, pricing changes, Azure Foundry implications, and a production checklist for routing teams.
- GuideDashScope October 2026 Model Sunset: 27-Day Last-Call Migration ChecklistOctober 10 is 27 days away. DashScope (Bailian) will hard-stop 100+ models — Qwen mainlines, snapshots, and every third-party model (DeepSeek, GLM, MiniMax, Kimi). QPM/TPM throttling is already underway. Here is the compact last-call checklist: audit your model IDs, swap replacements, get vendor-direct keys, and test before the deadline.
- GuideGPT-6 Astra vs Claude Fable 5.1 vs Gemini 3.8 Flash: September 2026 Routing Decision MatrixThree frontier models shipped within 72 hours in early September 2026. GPT-6 Astra and Claude Fable 5.1 share the same $10/$50 price tier but differ on cache economics and tool calling. Gemini 3.8 Flash undercuts both at $0.75/$3.75 while matching their coding benchmarks. We compare API surfaces, pricing, benchmarks, and routing strategies so you can pick the right model — or all three — for your workload.
July 2026
- NewsGrok 4.1 Is Being Removed from Google Cloud: The Routing Migration Every GEAP Operator Must Finish Before August 20Google Cloud's Gemini Enterprise Agent Platform shuts down Grok 4.1 Fast on August 20, 2026. API requests then return 400 — no fallback, no grace period. If your routing layer points to xai/grok-4.1-fast on GEAP, here is the migration decision matrix.
- GuideMCP Stateless Protocol Migration Guide: What the 2026-07-28 Release Candidate Changes for Every AI GatewayThe MCP 2026-07-28 specification removes session IDs and the initialize handshake. This step-by-step migration guide covers before/after code diffs, load balancer changes, SDK upgrades, the explicit-handle pattern, and a rollback path for every gateway operator.
- NewsDashScope Qwen Native Model Retirement October 2026: The Routing Audit Your Team Cannot SkipAlibaba Cloud Model Studio retires qwen-turbo, qwq-plus, qvq-max, qwen-vl-max, qwen-coder-turbo, qwen-tts, and the full paraformer ASR stack on October 10. QPM throttling has already started — here is the routing audit checklist.
- NewsAlibaba Bailian Retires DeepSeek, Kimi, MiniMax, and GLM Models on October 10: The Multi-Provider DashScope Routing AuditAlibaba Bailian retires DeepSeek V3/R1, Kimi K2, MiniMax M2.1, and GLM 4.6/4.7 proxies on October 10, 2026 — plus qwen-coder-plus and dozens of Qwen3 variants. QPM throttling has already begun; audit your DashScope model IDs now.
- GuideGPT-5.6 Programmatic Tool Calling: Migration Guide for Routing and Agent WorkflowsGPT-5.6 introduces Programmatic Tool Calling — the model writes JavaScript to orchestrate your tools inside a V8 sandbox, cutting token use by 24–63% and eliminating round-trip overhead. The catch: it only works on the Responses API. We walk through the migration from classic function calling, highlight every breaking change, and show how to route GPT-5.6 through an OpenAI-compatible gateway during the transition.openai/gpt-5.6-sol
- NewsDeepSeek deepseek-chat Retires July 24: The Gateway Routing Audit Every Operator Must Run This Weekdeepseek-chat and deepseek-reasoner stop responding at 15:59 UTC on July 24. With 7 days left, here is the routing audit checklist every AI gateway operator must complete before the cutoff hits production.
- GuideMigrating Off deepseek-chat and deepseek-reasoner Before July 24, 2026: Routing Audit and Drop-In ReplacementsDeepSeek retires the legacy model aliases deepseek-chat and deepseek-reasoner on July 24, 2026 at 15:59 UTC. Every API call using these names will fail after the cutoff. This guide walks through the exact replacement model IDs, code diffs, a production audit checklist, and how to update your routing configuration — all in under 10 minutes.deepseek/deepseek-v4
- GuideKimi K3 vs K2: What Changed, What Broke, and When to Upgrade Your RoutingMoonshot AI launched Kimi K3 on July 16, 2026 — a 2.8T-parameter flagship with a 1M-token context window, new reasoning_effort parameter, and $3/$15 pricing. We compare K3 against the K2 family (K2.6 and K2.7 Code) on API surface, pricing, benchmarks, and routing, and give you a concrete migration checklist.moonshot/kimi-k3
- GuideQwen3 → Qwen3.7 Migration Guide: What Changes When qwen3-max Retires October 10Five Qwen3 mainline models — qwen3-max, qwen3-max-preview, qwen3.6-max-preview, qwen3-coder-plus, and qwen3-vl-flash — retire on October 10, 2026, replaced by the Qwen3.7 generation. We mapped every retiring model to its drop-in replacement, compared pricing and capabilities, wrote the code diffs, and built a migration checklist.qwen/qwen3.7
- NewsKimi K2.6 Is Gone from NVIDIA NIM Today: Your Three Migration Paths to K2.7 CodeNVIDIA NIM shut down its Kimi K2.6 endpoint on July 7, 2026. If your routing config points to the NIM API for Kimi K2.6, requests are now failing. Here are the three concrete migration paths every operator must evaluate before end of day.moonshot/kimi-k2.6
- GuideOctober 2026 DashScope Model Sunset: Migration Guide for 100+ Retiring ModelsOn October 10, 2026, DashScope (Bailian) will retire 100+ models across four waves — Qwen3 mainlines, all legacy Qwen mainlines (qwen-turbo, qwq-plus, qvq-max), every third-party model (DeepSeek, MiniMax, GLM, Kimi), and 60+ snapshots. We mapped every retiring model to its replacement, wrote before/after code diffs, and built a migration checklist so you can switch before the deadline.
- NewsClaude Haiku Vertex AI Shutdown: Haiku Is Gone, Opus Is Next — Audit Your Partner-Model Routing NowClaude 3.5 Haiku shut down on Vertex AI yesterday. Claude 3 Opus is deprecated and exits August 1. If your routing policy lists either model on Vertex, you are already failing or will within 26 days.
- NewsGemini API Image Generation 2026: Fix Failed to Fetch After Preview ShutdownsGemini API image generation changed in 2026: preview image models now fail after the June 25 cutoff, and Imagen 4 GA endpoints shut down August 17. Audit model IDs, swap to gemini-3.1-flash-image or gemini-3-pro-image, and test generateContent before the next incident.
- GuideMigrating Off OpenAI Codex, Deep Research, and Computer Use Before the July 23 ShutdownOpenAI is retiring gpt-5-codex, o3-deep-research, computer-use-preview, gpt-4o-search-preview, and related model IDs on July 23, 2026. This migration guide covers the full replacement matrix, before/after code diffs, pricing delta, rollback options, and a TheRouter fallback config for the transition window.
- GuideClaude Opus Fast Mode Deprecated: Complete Migration Guide Before the July 24 Hard ErrorAnthropic deprecated fast mode on Claude Opus 4.7 on June 25, 2026 and will hard-error on July 24. This step-by-step guide covers the two failure modes (Opus 4.6 silent removal vs 4.7 hard error), codebase audit grep patterns, effort-level alternatives, cost comparison, and fallback routing strategies to keep your pipelines running.
- NewsOpenAI Retires Codex, Deep-Research, and Computer-Use Models on July 23: The 21-Day Routing Deadline Every Team Must ClearOn July 23, OpenAI shuts down gpt-5-codex, o3-deep-research, computer-use-preview, and 11 more model aliases. If your routing config still points to any of these, requests will fail. Here is what to audit now.
June 2026
- NewsClaude Opus Fast Mode: Two Different Failure Modes Every Routing Team Must Audit NowAnthropic removed fast mode from Opus 4.6 silently and is pulling it from Opus 4.7 on July 24 with a hard error. Two different failure modes — same 25-day window to act.
- GuideSeptember 2026 Qwen Model Sunset Migration Guide: qwen3-max, qwen3-coder-plus, and qwen3-vl-flash ReplacementsFive Qwen mainline models — qwen3-max, qwen3-max-preview, qwen3.6-max-preview, qwen3-coder-plus, and qwen3-vl-flash — sunset on September 8, 2026. We mapped every retiring model to its official replacement, compared pricing, wrote the code diffs, and built a step-by-step migration checklist so you can switch before the deadline.
- GuideOpenAI GPT-5 and O3 Snapshot Deprecation Guide: December 2026 Migration PlanningOpenAI deprecated six first-generation GPT-5 and O3 model snapshots on June 11, 2026, all shutting down December 11, 2026. This migration guide covers the full model-by-model replacement matrix, code diffs, pricing impact, rollback paths, and a production checklist for routing teams.
- GuideChinese AI Model Deprecation Calendar Q3 2026: DashScope, Anthropic, and OpenAI Sunset WavesEight active deprecation waves are hitting AI model APIs between July and December 2026 — DashScope alone sunsets 60+ model IDs across 4 waves. This unified calendar covers every upcoming sunset date, replacement model, and migration path across Alibaba Bailian, Anthropic, and OpenAI.
- NewsOpenAI Retires gpt-5 and o3 Snapshots on December 11: What Every Routing Team Must Audit NowOpenAI has deprecated six first-generation gpt-5 and o3 model snapshots, all shutting down December 11, 2026. Teams still routing to date-stamped IDs have six months to migrate — here's the full audit checklist.openai/gpt-5
- GuideAnthropic's 60-Day Deprecation Cadence: A Migration Playbook for Multi-Provider Routing TeamsAnthropic retires Claude models on a roughly 60-day cadence after deprecation notice. This playbook covers the lifecycle timeline from Opus 3 through Opus 4.8, concrete migration code diffs, fallback routing strategies, and a checklist for teams running multi-provider stacks.
- NewsMiMo V2 Flash Deprecation: June 18 Migration to V2.5 Changes Your API RoutingXiaomi MiMo completes its V2 → V2.5 migration on June 18: mimo-v2-flash and mimo-v2-tts auto-route to V2.5 successors at V2.5 pricing. Old model IDs in your routing config will silently change behavior and billing.
- NewsVertex AI Extensions Shut Down November 26: Three Migration Paths for Agent PlatformGoogle deprecated Vertex AI Extensions on May 26, 2026, with a hard shutdown on November 26. Teams routing agent workflows through Google must migrate their Code Interpreter, Search, and Custom Extensions to the Gemini Enterprise Agent Platform before the deadline.
- NewsTheRouter Deprecates /v1/anthropic/* Paths: Migrate to /v1/messages Before September 3, 2026TheRouter's legacy /v1/anthropic/messages paths are deprecated and will be removed on September 3, 2026. The canonical path is /v1/messages — the same path official Anthropic SDKs use. Migration is a one-line base-URL change.
- NewsIs Vertex AI Deprecated? Imagen and Veo Endpoint Shutdown List for June 30, 2026Vertex AI is not deprecated, but Google is retiring every Imagen 2.x/3.x/4.x and Veo 2.x/3.0 GA endpoint on June 30, 2026. Use this shutdown list to migrate image and video routing to gemini-2.5-flash-image and veo-3.1 endpoints.
- GuideQwen Legacy Tier Sunset 2026-07-13: Migrating qwen-turbo, qwen-vl-max, qwen-coder-plus, and QwQ/QVQ Before the DeadlineOn 2026-07-13 Bailian retires 10 Qwen legacy commercial tiers — qwen-turbo, qwen-vl-max, qwen-coder-plus, qwq-plus, qvq-max, and more. Full replacement matrix, code diffs, pricing delta, and rollback path before the deadline.
- GuideMigrating Off Bailian-Hosted DeepSeek, GLM, MiniMax, and Moonshot Before the 2026-07-08 SunsetAliyun Bailian sunsets a broad wave of third-party-model snapshots on 2026-07-08 — DeepSeek-V3/R1, MiniMax-M2.1, GLM-4.6/4.7, Moonshot Kimi-K2. Concrete replacement matrix, vendor-direct routing through TheRouter, code diffs, and a rollback path.
- GuideMigrate from OpenAI SDK to TheRouter: Base URL, Model IDs, and Rollback ChecklistStep-by-step migration guide: change two lines in your OpenAI SDK setup to route through TheRouter, map model IDs, add fallback chains, and keep a clean rollback path.
- NewsClaude Opus 4.1 Deprecation: Anthropic August 5 Migration Guide for Router TeamsAnthropic's Claude Opus 4.1 deprecation retires claude-opus-4-1-20250805 on August 5, 2026. Use this router-focused migration guide to replace aliases, audit fallback tiers, and avoid API failures.anthropic/claude-opus-4.1
- NewsDeepSeek Deprecates deepseek-chat Model Name: V4 Flash Migration and the New Anthropic API Routing PlaybookDeepSeek retires deepseek-chat and deepseek-reasoner on July 24, replacing them with explicit V4 model names and a new Anthropic API endpoint. Here is what changes for AI engineering teams routing through DeepSeek today.
- NewsOpenAI Evals Platform, Agent Builder, and Reusable Prompts Deprecated: November 2026 ShutdownOpenAI's evals platform deprecation, Agent Builder shutdown, and v1/prompts API removal all land November 30, 2026. Here's what operators need to migrate and how the routing layer absorbs the gap.
- NewsOpenAI gpt-image-2 Migration Guide for gpt-image-1, gpt-image-1.5, and chatgpt-image-latest APIsOfficial OpenAI gpt-image-2 migration checklist for teams still using gpt-image-1, gpt-image-1.5, gpt-image-1-mini, or chatgpt-image-latest before the Q4 2026 API shutdown.openai/chatgpt-image-latest · openai/gpt-image-1.5 · openai/gpt-image-1 · openai/gpt-image-2
May 2026
- NewsOpenAI's Biggest Deprecation Wave Yet: gpt-4, o1, o4-mini, and 25+ Models Shut Down by October 2026OpenAI's April 22 deprecation notice covers 25+ model IDs across two hard shutdown dates — July 23 and October 23, 2026. If your routing config still references gpt-4, gpt-3.5-turbo, o1, o3-mini, or o4-mini, you have a breaking change on the calendar.openai/o4-mini
- NewsVertex AI SDK Deprecated: Migration Deadline June 24, 2026 — What Routing Teams Need to KnowThe Vertex AI generative AI SDK is deprecated — its modules are removed June 24, 2026. If your team routes to Google via vertexai.generative_models or related imports, here's exactly what to migrate to keep production code working.
- NewsGemini 2.0 Flash Shutdown & EOL June 2026: What Replaced It and What to Do NowGemini 2.0 Flash and Flash-Lite hit end-of-life June 1, 2026 — the shutdown is done. Here is what model IDs were removed, which replacements (gemini-2.5-flash-lite, gemini-3.1-flash-lite) actually work as substitutes, the real cost delta, and the fastest way to audit…
- NewsDeepSeek API Model Names 2026: deepseek-chat → deepseek-v4-flash, deepseek-reasoner → deepseek-v4-pro | Deprecation July 24DeepSeek API model names changed 2026: deepseek-chat becomes deepseek-v4-flash and deepseek-reasoner merges into deepseek-v4-flash (thinking mode) or deepseek-v4-pro (1M context). Deprecated July 24, 2026. New Anthropic-compatible endpoint at /anthropic for Claude Code routing.deepseek/deepseek-v4-flash · deepseek/deepseek-v4-pro