claude code 2.1.299
Claude Code
- Added `size`, `weight`, `mono` and `tabular` to a mod's `Text` and named spacing steps (`xs` to `xl`) to its `Box`; `bold` is deprecated in favor of `weight`
Deprecations, retirements and shutdowns from the official sources ClaudeMon reads, newest first. Subscribe with the deprecations feed in Atom, RSS or JSON Feed.
A change counts when an official listing gives a shutdown, retirement or deprecation date, or a lifecycle past active. It also counts when its title or text names a deprecation, retirement, sunset, shutdown, end of life or discontinuation that is not negated. Dates are the ones the listing or text names.
Claude Code
- Added `size`, `weight`, `mono` and `tabular` to a mod's `Text` and named spacing steps (`xs` to `xl`) to its `Box`; `bold` is deprecated in favor of `weight`
Claude Code
- Deprecated MCP wizard interface in favor of other MCP commands
Claude Code
- Deprecated claude config commands in favor of editing settings.json
Claude Code
- Deprecated piped input in interactive mode
Claude Code
- Remove deprecated .claude.json allowedTools, ignorePatterns, env, and todoFeatureEnabled config options (instead, configure these in your settings.json)
Claude Code
- Deprecated output styles.
Claude Code
- Added `attribution` setting to customize commit and PR bylines (deprecates `includeCoAuthoredBy`)
Claude Code
- Added deprecation notification for npm installations - run `claude install` or see https://code.claude.com/docs/en/setup for more options
Claude Code
- Deprecated Windows managed settings path `C:\ProgramData\ClaudeCode\managed-settings.json` - administrators should migrate to `C:\Program Files\ClaudeCode\managed-settings.json`
Claude Code
- Fixed `--model claude-opus-4-0` and `--model claude-opus-4-1` resolving to deprecated Opus versions instead of current
Claude Code
- Deprecated `/output-style` command — use `/config` instead.
Claude Code
- Breaking change: Removed deprecated Windows managed settings fallback at `C:\ProgramData\ClaudeCode\managed-settings.json` — use `C:\Program Files\ClaudeCode\managed-settings.json`
Claude Code
- Deprecated `TaskOutput` tool in favor of using `Read` on the background task's output file path
Claude Code
- Added `ENABLE_PROMPT_CACHING_1H` env var to opt into 1-hour prompt cache TTL on API key, Bedrock, Vertex, and Foundry (`ENABLE_PROMPT_CACHING_1H_BEDROCK` is deprecated but still honored), and `FORCE_PROMPT_CACHING_5M` to force 5-minute TTL
Claude Code
- Fixed `/review` using a deprecated `projectCards` GraphQL query that errored on repos with Classic Projects
Claude Code
- `claude --bg --dangerously-skip-permissions` now persists across retire→wake
Claude Code
- Deprecated `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` (will be removed on 06/01).
Claude Code
- Fixed `claude --bg --dangerously-skip-permissions` not persisting across retire/wake
Claude Code
- Empty idle background sessions left over from `←` are now automatically retired by the daemon after 5 minutes
Claude Code
- Background sessions now preserve `--ide`, `--chrome`, `--bare`, `--remote-control`, and other flags across retire→wake, and respawn state validation was hardened
Claude Code
- Fixed background sessions re-attached after overnight retire losing their conversation and re-running the original prompt
Claude Code
- Fixed a misleading "MCP server disconnected" notice for intentionally retired tools when resuming older sessions
Claude Code
- Added a warning when the requested model is deprecated or automatically updated to a newer model, shown on stderr in print mode (`-p`) and now also covering models set in agent frontmatter
Claude Code
- Deprecated the Task tool's `mode` parameter (now ignored); subagents inherit the parent session's permission mode by default
Claude Code
- Fixed tool errors not being displayed for tools no longer available locally, for example after an MCP server is removed
Claude Code
- [VSCode] "Report a problem" and `/bug` now open the built-in feedback dialog instead of a retired survey link
Claude Code
- Fixed cloud sessions occasionally being marked as lost when the environment shut down while Claude was waiting on a permission prompt
Claude Code
- Fixed self-hosted runner sessions released on idle, retire, or startup timeout occasionally resuming on another runner before the post-session hook had finished
Claude Code
- [VSCode] Fixed a session teleported from Claude Code on the web treating a question that was cut off when the cloud session shut down as declined
Claude Code
- Fixed background (`--bg`) sessions occasionally being retired mid-turn when a message arrived just before the idle timeout
Claude Code
- Fixed background sessions left running an older Claude Code binary piling up across auto-updates instead of being retired
Claude Code
- Fixed `--tools` and `--restricted` not applying to built-in tools that register after launch, and deprecated tool names reaching tools outside the caller's tool set
Claude Code
- Changed background sessions whose scheduled task is gone: they now move to Completed about 20 seconds later and can be updated or shut down when idle
Claude Code
- Self-hosted runner: Fixed a turn that ended right at a `--retire-at` release losing its finished signal; the runner now briefly waits for the turn to be reported before stopping the session
Claude Code
- Removed the deprecated TaskOutput tool; Claude reads a background task's output file with Read instead, and the `taskOutputMaxChars` setting and `TASK_MAX_OUTPUT_LENGTH` no longer have any effect
Claude Code
- [Claude Tag] Fixed Slack threads whose model has been retired falling back to another model on every reply, slower and with a fallback note each time; the thread now moves to a working model
Claude API, published
Retirement Shutdown date, from the official listing:
On September 30, 2026, Anthropic notified developers using Claude Sonnet 4.5 of its upcoming retirement on the Claude API.
Dates named: ,
Claude Platform, published
- We announced the deprecation of the Claude Sonnet 4.5 model (claude-sonnet-4-5-20250929), with retirement on the Claude API scheduled for November 30, 2026.
Dates named:
Claude Platform, published
v1.0 requires Python 3.10 or later and removes long-deprecated surface, including the legacy Text Completions API, the temperature, top_p, and top_k parameters on Messages methods, and the tool runner's client-side compaction_control.
Claude Platform, published
- We've retired the Claude Opus 4.1 model (claude-opus-4-1-20250805).
Claude Platform, published
- The legacy Workbench (platform.claude.com/workbench) in the Claude Console is being sunset with access ending on August 17, 2026.
Dates named:
Claude Platform, published
Three behavior changes apply when migrating: adaptive thinking is now on by default; manual extended thinking (thinking: {type: "enabled", budget_tokens: N}) is removed and returns a 400 error (it was deprecated on Sonnet 4.6); and setting sampling parameters (temperature, top_p, top_k) to non-default values returns a 400 error.
Claude Platform, published
- We've deprecated fast mode for Claude Opus 4.7, with removal on July 24, 2026.
Dates named:
Claude Platform, published
- We've retired the Claude Sonnet 4 model (claude-sonnet-4-20250514) and the Claude Opus 4 model (claude-opus-4-20250514).
Claude API, published
Retirement Shutdown date, from the official listing:
This model was retired August 5, 2026.
Dates named: ,
Claude Platform, published
- We announced the deprecation of the Claude Opus 4.1 model (claude-opus-4-1-20250805), with retirement on the Claude API scheduled for August 5, 2026.
Dates named:
Claude Platform, published
- We've deprecated fast mode for Claude Opus 4.6, with removal approximately 30 days after launch.
Claude Platform, published
- We've retired the 1M token context window beta (context-1m-2025-08-07) for Claude Sonnet 4.5 and Claude Sonnet 4.
Dates named:
Claude Platform, published
- We've retired the Claude Haiku 3 model (claude-3-haiku-20240307).
Claude API, published
Retirement Shutdown date, from the official listing:
These models were retired June 15, 2026.
Dates named: ,
Showing the newest 50. Older ones are in the Changes API with lab=anthropic and kind=deprecation.
OpenAI API
Inference on fine-tuned models will continue to be available until the base models are deprecated.
Dates named:
Codex, published
Configurations using the retired shell flags receive a migration notice.
OpenAI Product Changelog, published
Configurations using the retired shell flags receive a migration notice.
OpenAI API, published
Retirement Shutdown date, from the official listing:
On October 14, 2026, we notified developers using certain GPT-4 series models of their deprecation and removal from the API on January 14, 2027.
Dates named: ,
OpenAI Product Changelog, published
# GPT-5.5 retirement in Codex
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
The following text-to-speech models are deprecated and will be removed from the API on January 6, 2027, with at least three months' notice.
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
The following models are deprecated and will be removed from the API on April 1, 2027, with six months' notice.
Dates named:
OpenAI Product Changelog, published
- #47065 Deduplicate deprecation notices in the TUI transcript @etraut-openai
OpenAI Product Changelog, published
- Clarify that deprecated friendly and pragmatic personality settings no longer select response styles.
OpenAI Product Changelog, published
# GPT-5.5 retires from ChatGPT, ChatGPT Work, and Codex on October 14
Dates named:
OpenAI Product Changelog, published
# GPT-5.3-Codex-Spark deprecated
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
The `gpt-5.4-cyber` model is deprecated and will be removed from the API on October 1, 2026.
Dates named:
OpenAI Product Changelog, published
been removed after their deprecation on August 24, 2026.
Dates named:
OpenAI API, published
Announced the deprecation of `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `gpt-4o-transcribe-diarize`.
Dates named: ,
OpenAI API, published
Retirement Shutdown date, from the official listing:
On August 26, 2026, we notified developers using `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `gpt-4o-transcribe-diarize` of their deprecation and removal from the API on February 26, 2027.
Dates named: ,
OpenAI Product Changelog, published
# Codex MCP server command deprecated
OpenAI Product Changelog, published
# GPT-5.4 and GPT-5.4 mini retire from Codex on August 31
OpenAI API, published
Retirement Shutdown date, from the official listing:
On July 20, 2026, we notified developers using legacy audio, realtime, and transcription model families and snapshots of their deprecation and removal from the API on January 20, 2027.
Dates named: ,
OpenAI API, published
Retirement Shutdown date, from the official listing:
On June 11, 2026, we notified developers using older GPT-5 and o3 model snapshots of their deprecation and removal from the API on December 11, 2026.
Dates named: ,
OpenAI API, published
Announced the deprecation of reusable prompt objects, the Evals platform, and Agent Builder.
OpenAI API, published
On June 3, 2026, we notified developers using reusable prompts in the dashboard and API that reusable prompt objects are being deprecated.
Dates named: ,
OpenAI API, published
On June 3, 2026, we notified developers using Agent Builder that the product is being deprecated.
Dates named: ,
OpenAI API, published
On June 3, 2026, we notified developers using the Evals platform that the product is being deprecated.
Dates named: ,
OpenAI API, published
Retirement Shutdown date, from the official listing:
On June 2, 2026, we notified developers using older GPT Image models of their deprecation and removal from the API on December 1, 2026.
Dates named: ,
OpenAI Product Changelog, published
# GPT-5.3-Codex and GPT-5.2 deprecated
OpenAI API, published
Deprecated DALL·E model snapshots and the Realtime API Beta.
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
On May 8th, 2026, we notified developers using `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots of their deprecation and removal from the API.
Dates named: ,
OpenAI API, published
Retirement Shutdown date, from the official listing:
On April 22, 2026, we announced the deprecation of the following older OpenAI models.
Dates named: ,
OpenAI API, published
Retirement Shutdown date, from the official listing:
To improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models.
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
On March 24th, 2026, we notified developers using the Videos API and Sora 2 video generation model aliases and snapshots of their deprecation and removal from the API on September 24, 2026.
Dates named: ,
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
This will replace `POST /v1/videos/{video_id}/remix`, which will be deprecated in `6` months.
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI Product Changelog, published
# Custom prompts deprecated
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
On November 18th, 2025, we notified developers using `chatgpt-4o-latest` model snapshot of its deprecation and removal from the API on February 17, 2026.
Dates named: ,
OpenAI API, published
Retirement Shutdown date, from the official listing:
On November 17th, 2025, we notified developers using `codex-mini-latest` model of its deprecation and removal from the API on February 12, 2026.
Dates named: ,
OpenAI API, published
Retirement Shutdown date, from the official listing:
On November 14th, 2025, we notified developers using DALL·E model snapshots of their deprecation and removal from the API on May 12, 2026.
Dates named: ,
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
OpenAI API, published
Retirement Shutdown date, from the official listing:
Dates named:
Showing the newest 50. Older ones are in the Changes API with lab=openai and kind=deprecation.
Gemini API
Gemini API
Gemini API
Gemini API
Gemini API
Gemini API
Gemini API
Gemini API
Gemini API
Gemini API
Retirement Shutdown date, from the official listing:
Dates named:
Gemini API
Retirement Shutdown date, from the official listing:
Dates named:
Gemini API
Gemini API
Gemini API
Gemini API, published
- **Gemini 3.7 Flash deprecation** : [`gemini-3.7-flash`](https://ai.google.dev/gemini-api/docs/whats-new-gemini-3.7) is deprecated and has been replaced by [`gemini-3.8-flash`](https://ai.google.dev/gemini-api/docs/whats-new-gemini-3.8).
Gemini API, published
- **Deprecation announcement** : The `gemini-3.1-flash-image` model is
Gemini API, published
which replaces and deprecates `antigravity-preview-05-2026`.
Gemini API, published
The existing `gemini-omni-flash-preview` endpoint will be deprecated on
Gemini API, published
- **Deprecation announcement** : The `gemini-robotics-er-1.6-preview` model
Dates named:
Gemini API, published
- **Deprecated parameters** : The sampling parameters `temperature`, `top_p`
Gemini API, published
- **Deprecation announcement** : The following image generation models are
Dates named: , ,
Gemini API, published
- The following Gemini 2.0 models are now [shut down](https://ai.google.dev/gemini-api/docs/deprecations):
Gemini API, published
- Deprecation announcement: The `gemini-3.1-flash-image-preview` and
Dates named:
Gemini API, published
- The `gemini-3.1-flash-lite-preview` model has been [shut down](https://ai.google.dev/gemini-api/docs/deprecations).
Gemini API, published
- Deprecation announcement: The `gemini-3.1-flash-lite-preview` model is
Dates named:
Gemini API, published
- The `gemini-robotics-er-1.5-preview` model has been [shut down](https://ai.google.dev/gemini-api/docs/deprecations).
Gemini API, published
- Deprecation announcement: The `gemini-robotics-er-1.5-preview` model
Dates named:
Gemini API, published
- The `gemini-2.5-flash-lite-preview-09-2025` model has been shut down.
Gemini API, published
- Deprecation announcement: The `gemini-2.5-flash-lite-preview-09-2025` model
Dates named:
Gemini API, published
- The Gemini 3 Pro Preview model has been [shut down](https://ai.google.dev/gemini-api/docs/deprecations).
Gemini API, published
- Deprecation announcement: Gemini 3 Pro Preview (`gemini-3-pro-preview`)
Dates named:
Gemini API, published
- Deprecation announcement: The following models will be
Dates named:
Gemini API, published
- The following models are [shut down](https://ai.google.dev/gemini-api/docs/deprecations):
Gemini API, published
- Deprecation announcement: The following models will be
Dates named:
Gemini API, published
- The `text-embedding-004` model has been [shut down](https://ai.google.dev/gemini-api/docs/deprecations).
Gemini API, published
stage and deprecation timeline.
Gemini API, published
- The following Gemini Live API models are now shut down:
Gemini API, published
- Deprecation announcement: The `gemini-2.5-flash-image-preview` model will be shut down January 15, 2026.
Dates named:
Gemini API, published
- Deprecation announcement: The `text-embedding-004` model will be shut down January 14, 2026.
Dates named:
Gemini API, published
- Deprecation announcement: The following models will be shut down:
Gemini API, published
- The following model is shut down:
Gemini API, published
- Deprecation announcement: The following models will be shut down:
Gemini API, published
- The following Gemini Live API models are now shut down:
Gemini API, published
- Deprecation announcement: Shut down for `veo-3.0-generate-preview` and
Gemini API, published
- The following Gemini 1.5 models are now shut down:
Gemini API, published
- Deprecation announcement: The following models will be shut down in October 2025:
Gemini API, published
Support for using URL context with the `gemini-2.0-flash` model (available during experimental release) will be discontinued in one week.
Gemini API, published
The `gemini-embedding-exp-03-07` model will be deprecated on August 14, 2025.
Dates named:
Gemini API, published
- `gemini-2.5-pro-exp-03-25` is shut down.
Gemini API, published
`gemini-2.5-flash-preview-04-17` will be deprecated on July 15, 2025.
Dates named:
Showing the newest 50. Older ones are in the Changes API with lab=google and kind=deprecation.
Grok API
| Speech to Speech (grok-voice-2.0) — Deprecated | $0.08 / min ($4.80 / hr)<br />$0.004 / text input |
Grok API, published
grok-voice-2.0 is deprecated.
Grok API, published
grok-voice-transcribe-1.0 is deprecated and reaches end of life on October 2, 2026.
Dates named:
Grok API, published
On November 2, 2026, grok-imagine-image-quality is retired.
Dates named:
Muse Code
- The task panel no longer glitches while old checkpoints are retired
Muse Code
- Shutting down many stdio MCP servers at once no longer stalls: they share one scan of the process table instead of each scanning every process on the machine
Muse Code
- /new and /clear prepare the new session before shutting down the old one, so both stay resumable if the process dies mid-restart; /new now clears the visible thread like /clear, both share one palette description, and quitting after keeping background tasks across them warns that those tasks will be stopped
Muse Code
- Switching sessions no longer fails when the previous session is slow to shut down
Muse Code
- The host-network sandbox mode is now spelled unrestricted (--sandbox-network unrestricted, network.mode: unrestricted); enabled still works as a deprecated silent alias
Llama TypeScript SDK, published
* **internal:** remove deprecated `compilerOptions.baseUrl` from tsconfig.json ([f77cba7](https://github.com/meta-llama/llama-api-typescript/commit/f77cba7e13e1c7420e065b497413987529502e76))