Moonshot v1 (8k / 32k / 128k) Deprecation, Shutdown Dates & Migration Guide

Runs locally in your browser — 0 bytes uploaded Synced 2026-11-12 UTC · 7 variants · 1 ecosystems

Track confirmed UTC deprecation and shutdown dates for Moonshot v1 (8k / 32k / 128k) (Moonshot AI) across Moonshot AI. Preview moonshot-v1-128k → kimi-k3.1-pro upgrades locally below, audit full configs in the Model Config Auditor, or benchmark token pricing in DevToken.

Tracked Variants 7
Earliest Upcoming EOL RETIRED
Recommended Upgrade kimi-k3.1-pro
Ecosystems Covered Moonshot AI

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

Replacement Diff Preview (moonshot-v1-128k → kimi-k3.1-pro)

# MOONSHOT_MODEL: moonshot-v1-128k -> kimi-k3.1-pro [RETIRED]
- MOONSHOT_MODEL="moonshot-v1-128k"
+ MOONSHOT_MODEL="kimi-k3.1-pro"

# model: moonshot-v1-128k -> kimi-k3.1-pro [RETIRED]
- model: moonshot/moonshot-v1-128k
+ model: moonshot/kimi-k3.1-pro

2. Cross-Ecosystem Moonshot v1 (8k / 32k / 128k) Lifecycle Matrix (7)

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.

Moonshot v1 (8k / 32k / 128k) lifecycle status, UTC shutdown dates, and replacement models across Moonshot AI
Model ID Provider Calculated Status Confirmed Shutdown (UTC) Vendor Lifecycle Replacement & Migration Source
moonshot-v1-128k Moonshot AI RETIRED Not announced Retired
kimi-k3.1-pro Cost → Audit →
Docs ↗
moonshot-v1-128k-vision-preview Moonshot AI RETIRED Not announced Retired
kimi-k3.1-pro Cost → Audit →
Docs ↗
moonshot-v1-32k Moonshot AI RETIRED Not announced Retired Docs ↗
moonshot-v1-32k-vision-preview Moonshot AI RETIRED Not announced Retired
kimi-k3.1-pro Cost → Audit →
Docs ↗
moonshot-v1-8k Moonshot AI RETIRED Not announced Retired Docs ↗
moonshot-v1-8k-vision-preview Moonshot AI RETIRED Not announced Retired
kimi-k3.1-pro Cost → Audit →
Docs ↗
moonshot-v1-auto Moonshot AI RETIRED Not announced Retired Docs ↗

3. Production Migration Checklist (moonshot-v1-128k → kimi-k3.1-pro)

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 MOONSHOT_MODEL, moonshot/ LiteLLM routes, and dated snapshot strings in the Moonshot v1 (8k / 32k / 128k) family (0 deprecated, 7 retired, 0 active variants tracked).
  2. Benchmark successor quality & token pricing: Validate structured output schemas, tool-calling payloads, and latency against kimi-k3.1-pro, 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 Moonshot v1 (8k / 32k / 128k) identifiers cannot re-enter production.

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

5. Moonshot v1 (8k / 32k / 128k) Deprecation & Upgrade FAQ

Is Moonshot v1 (8k / 32k / 128k) deprecated or retired across Moonshot AI?

LLMEOL tracks 7 Moonshot v1 (8k / 32k / 128k) variants across Moonshot AI: 0 deprecated with scheduled shutdowns, 7 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 moonshot-v1-128k?

The primary recommended upgrade target for moonshot-v1-128k is kimi-k3.1-pro. Always test prompt formatting, max output tokens, and tool schemas on kimi-k3.1-pro, and compare token pricing in DevToken before switching production traffic.

How can I replace moonshot-v1-128k in .env and LiteLLM configs safely?

Paste your MOONSHOT_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.