{"total":59,"limit":25,"offset":0,"graves":[{"slug":"code-davinci-002","name":"Codex","kind":"model","provider":"OpenAI","modelId":"code-davinci-002","aliases":[],"born":"2021-08-10","died":"2024-01-04","retirementScheduled":null,"causeOfDeath":"withdrawn","successor":"gpt-3.5-turbo-instruct","epitaph":"The model that turned an English comment into a working function, and the engine underneath the first version of GitHub Copilot. It was given three days' notice; researchers who had pinned their baselines to it lost their control group overnight, access was extended for research use, and the endpoint was finally closed on 4 January 2024. The name came back in 2025 for something else entirely.","url":"https://models.rip/code-davinci-002/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://techcrunch.com/2021/08/10/openai-upgrades-its-natural-language-ai-coder-codex-and-kicks-off-private-beta/"]},{"slug":"text-davinci-003","name":"text-davinci-003","kind":"model","provider":"OpenAI","modelId":"text-davinci-003","aliases":[],"born":"2022-11-28","died":"2024-01-04","retirementScheduled":null,"causeOfDeath":"superseded","successor":"gpt-3.5-turbo-instruct","epitaph":"For a few months it was simply what people meant when they said \"the API\": a prompt went in, a completion came out, and there was no system message, no role and no conversation to manage. It taught a generation of developers what a prompt was, and then ChatGPT launched two days after it and took the room.","url":"https://models.rip/text-davinci-003/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://en.wikipedia.org/wiki/GPT-3"]},{"slug":"gpt-4","name":"GPT-4","kind":"model","provider":"OpenAI","modelId":"gpt-4","aliases":["gpt-4-0314","gpt-4-0613","gpt-4-completions","gpt-4-0613-completions"],"born":"2023-03-14","died":null,"retirementScheduled":"2026-10-23","causeOfDeath":"superseded","successor":"gpt-4-turbo","epitaph":"Eight thousand tokens of context at thirty dollars a million, and for most of 2023 the only model anyone trusted with a hard problem. The March snapshot went after three years, kept breathing by evaluation suites pinned to it since launch week and by people who never believed the newer models were the same. The June one is what a bare call to gpt-4 still resolves to, and it has until 23 October.","url":"https://models.rip/gpt-4/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://en.wikipedia.org/wiki/GPT-4"]},{"slug":"gpt-4-vision-preview","name":"GPT-4 with Vision (preview)","kind":"model","provider":"OpenAI","modelId":"gpt-4-vision-preview","aliases":[],"born":"2023-11-06","died":"2024-12-06","retirementScheduled":null,"causeOfDeath":"superseded","successor":"gpt-4-turbo","epitaph":"The first OpenAI endpoint you could hand a photograph. It never lost the word \"preview\" from its name: thirteen months after DevDay it was folded into GPT-4 Turbo, and looking at an image stopped being a separate model you had to opt into.","url":"https://models.rip/gpt-4-vision-preview/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://developers.openai.com/api/docs/changelog"]},{"slug":"gpt-4-turbo","name":"GPT-4 Turbo","kind":"model","provider":"OpenAI","modelId":"gpt-4-turbo","aliases":["gpt-4-turbo-2024-04-09","gpt-4-1106-preview","gpt-4-0125-preview","gpt-4-turbo-preview","gpt-4-turbo-preview-completions","gpt-4-turbo-completions"],"born":"2024-04-09","died":null,"retirementScheduled":"2026-10-23","causeOfDeath":"superseded","successor":null,"epitaph":"A hundred and twenty-eight thousand tokens of context at a third of GPT-4's input price and half its output, which is why so much production code was written against this exact model string and never moved. Its shutdown has a date on it. The endpoint is still answering.","url":"https://models.rip/gpt-4-turbo/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://developers.openai.com/api/docs/models/gpt-4-turbo","https://developers.openai.com/api/docs/models/gpt-4"]},{"slug":"gpt-3.5-turbo-instruct","name":"GPT-3.5 Turbo Instruct","kind":"model","provider":"OpenAI","modelId":"gpt-3.5-turbo-instruct","aliases":[],"born":"2023-09-18","died":null,"retirementScheduled":"2026-09-28","causeOfDeath":"superseded","successor":null,"epitaph":"The last model on the completions endpoint: no roles, no messages, just text in and text out, the interface the whole field started with. It was shipped as a bridge for developers who had not moved to chat yet, and it has outlived nearly every model that was meant to replace it. Its grave is dug and waiting.","url":"https://models.rip/gpt-3.5-turbo-instruct/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://developers.openai.com/api/docs/models/gpt-3.5-turbo-instruct","https://news.ycombinator.com/item?id=37558911","https://the-decoder.com/openai-releases-new-language-model-instructgpt-3-5/"]},{"slug":"o1-preview","name":"o1-preview","kind":"model","provider":"OpenAI","modelId":"o1-preview","aliases":[],"born":"2024-09-12","died":"2025-07-28","retirementScheduled":null,"causeOfDeath":"superseded","successor":"o1","epitaph":"The first model sold on the promise that it would think before it answered, and the first to bill you for tokens you were never allowed to read. It made a thirty-second wait feel like a feature rather than a fault, and every reasoning model since has been built on that bargain.","url":"https://models.rip/o1-preview/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://developers.openai.com/api/docs/changelog"]},{"slug":"gpt-4.5-preview","name":"GPT-4.5","kind":"model","provider":"OpenAI","modelId":"gpt-4.5-preview","aliases":[],"born":"2025-02-27","died":"2025-07-14","retirementScheduled":null,"causeOfDeath":"superseded","successor":null,"epitaph":"OpenAI's largest model, at seventy-five dollars a million input tokens, withdrawn from the API four and a half months after it arrived. It was the last serious attempt to get better by getting bigger, and it landed in the same season the field decided the answer was to think for longer instead.","url":"https://models.rip/gpt-4.5-preview/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://developers.openai.com/api/docs/models/gpt-4.5-preview"]},{"slug":"gpt-3.5-turbo","name":"GPT-3.5 Turbo","kind":"model","provider":"OpenAI","modelId":"gpt-3.5-turbo","aliases":["gpt-3.5-turbo-0301","gpt-3.5-turbo-0613","gpt-3.5-turbo-16k-0613","gpt-3.5-turbo-1106","gpt-3.5-turbo-0125","gpt-3.5-turbo-completions"],"born":"2023-03-01","died":null,"retirementScheduled":"2026-10-23","causeOfDeath":"superseded","successor":null,"epitaph":"Two dollars a million tokens, ten times cheaper than the GPT-3.5 models it replaced, and the model the first generation of chat apps was written against. The list of messages with roles that it introduced is still the shape of the industry's API. Its three snapshots leave on three separate dates, the first in September 2024 and the last on 23 October 2026.","url":"https://models.rip/gpt-3.5-turbo/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://web.archive.org/web/20240428215355/https://openai.com/blog/introducing-chatgpt-and-whisper-apis"]},{"slug":"dall-e-3","name":"DALL·E 3","kind":"model","provider":"OpenAI","modelId":"dall-e-3","aliases":[],"born":"2023-11-06","died":"2026-05-12","retirementScheduled":null,"causeOfDeath":"superseded","successor":"gpt-image-1","epitaph":"The image model that finally read the whole prompt, because it quietly rewrote your prompt into a longer one before drawing anything — which was either the reason it worked or the reason you could never get back exactly what you asked for. It was removed on the same day as DALL·E 2, and the name that had put image generation in front of the public went with them.","url":"https://models.rip/dall-e-3/epitaph","sources":["https://developers.openai.com/api/docs/deprecations","https://developers.openai.com/api/docs/changelog"]},{"slug":"claude-2.0","name":"Claude 2","kind":"model","provider":"Anthropic","modelId":"claude-2.0","aliases":[],"born":"2023-07-11","died":"2025-07-21","retirementScheduled":null,"causeOfDeath":"superseded","successor":"claude-2.1","epitaph":"Anthropic shipped the hundred-thousand-token window in May; Claude 2 was the one anyone could walk up to and use it, the first Claude behind a public URL instead of a waitlist. Pasting an entire book into the box stopped being a demo someone else had run and became a thing you did on a Tuesday.","url":"https://models.rip/claude-2.0/epitaph","sources":["https://platform.claude.com/docs/en/about-claude/model-deprecations","https://www.anthropic.com/news/claude-2","https://www.anthropic.com/news/100k-context-windows"]},{"slug":"claude-3-opus","name":"Claude 3 Opus","kind":"model","provider":"Anthropic","modelId":"claude-3-opus-20240229","aliases":["claude-3-opus-20240229"],"born":"2024-03-04","died":"2026-01-05","retirementScheduled":null,"causeOfDeath":"superseded","successor":"claude-opus-4","epitaph":"The first model from anyone that people openly preferred to GPT-4, and for most of 2024 the most expensive thing you could call from a terminal. It was retired with an unusual undertaking attached: Anthropic committed to keeping its weights, which is not the same as keeping the model running, but is more than anyone had promised before.","url":"https://models.rip/claude-3-opus/epitaph","sources":["https://platform.claude.com/docs/en/about-claude/model-deprecations","https://www.anthropic.com/news/claude-3-family","https://www.anthropic.com/research/deprecation-commitments"]},{"slug":"claude-3-haiku","name":"Claude 3 Haiku","kind":"model","provider":"Anthropic","modelId":"claude-3-haiku-20240307","aliases":["claude-3-haiku-20240307"],"born":"2024-03-13","died":"2026-04-20","retirementScheduled":null,"causeOfDeath":"superseded","successor":"claude-3-5-haiku","epitaph":"Twenty-five cents a million tokens bought two hundred thousand tokens of context, and that arithmetic quietly ran the classifiers, routers and cleanup jobs that nobody wrote posts about. It outlived both of the models it launched beside — Opus and Sonnet, the two the announcements were actually about.","url":"https://models.rip/claude-3-haiku/epitaph","sources":["https://platform.claude.com/docs/en/about-claude/model-deprecations","https://www.anthropic.com/news/claude-3-haiku"]},{"slug":"claude-3-5-sonnet","name":"Claude 3.5 Sonnet","kind":"model","provider":"Anthropic","modelId":"claude-3-5-sonnet-20240620","aliases":["claude-3-5-sonnet-20240620","claude-3-5-sonnet-20241022"],"born":"2024-06-20","died":"2025-10-28","retirementScheduled":null,"causeOfDeath":"superseded","successor":"claude-3-7-sonnet","epitaph":"Ask it for a chart and a second pane opened beside the conversation with the chart already running in it. Artifacts shipped the day this model did, and the layout it introduced — talk on the left, working software on the right — is the shape every AI coding tool settled into afterwards.","url":"https://models.rip/claude-3-5-sonnet/epitaph","sources":["https://platform.claude.com/docs/en/about-claude/model-deprecations","https://www.anthropic.com/news/claude-3-5-sonnet","https://aws.amazon.com/about-aws/whats-new/2024/06/anthropic-claude-3-5-sonnet-model-bedrock/","https://www.anthropic.com/news/3-5-models-and-computer-use"]},{"slug":"claude-3-7-sonnet","name":"Claude 3.7 Sonnet","kind":"model","provider":"Anthropic","modelId":"claude-3-7-sonnet-20250219","aliases":["claude-3-7-sonnet-20250219"],"born":"2025-02-24","died":"2026-02-19","retirementScheduled":null,"causeOfDeath":"superseded","successor":"claude-sonnet-4","epitaph":"The first Claude that would show you its reasoning if you asked and skip it if you did not, on one model and one endpoint rather than two. It shipped alongside a command-line agent that carried its name, and within a year the agent was better known than the model that came with it.","url":"https://models.rip/claude-3-7-sonnet/epitaph","sources":["https://platform.claude.com/docs/en/about-claude/model-deprecations","https://www.anthropic.com/news/claude-3-7-sonnet"]},{"slug":"claude-instant-1.2","name":"Claude Instant 1.2","kind":"model","provider":"Anthropic","modelId":"claude-instant-1.2","aliases":[],"born":"2023-08-09","died":"2024-11-06","retirementScheduled":null,"causeOfDeath":"superseded","successor":"claude-3-haiku","epitaph":"The cheap Claude, before there was a naming convention for cheap Claudes: Anthropic described it as carrying the strengths of Claude 2 into something faster and more affordable, which is where a great deal of unglamorous production traffic quietly went. Seven model IDs were switched off together on 6 November 2024 — the whole Claude 1 line, and the oldest entry in Anthropic's deprecation history.","url":"https://models.rip/claude-instant-1.2/epitaph","sources":["https://platform.claude.com/docs/en/about-claude/model-deprecations","https://www.anthropic.com/news/releasing-claude-instant-1-2"]},{"slug":"claude-2.1","name":"Claude 2.1","kind":"model","provider":"Anthropic","modelId":"claude-2.1","aliases":[],"born":"2023-11-21","died":"2025-07-21","retirementScheduled":null,"causeOfDeath":"superseded","successor":"claude-3-opus","epitaph":"It doubled the window to two hundred thousand tokens, and within a fortnight someone had hidden a single sentence in the middle of one and published what came back. Anthropic replied with a post showing that adding one line — \"Here is the most relevant sentence in the context:\" — moved recall from 27% to 98%. The headline was the window; the durable lesson was about how you ask.","url":"https://models.rip/claude-2.1/epitaph","sources":["https://platform.claude.com/docs/en/about-claude/model-deprecations","https://www.anthropic.com/news/claude-2-1","https://claude.com/blog/claude-2-1-prompting"]},{"slug":"claude-3-sonnet","name":"Claude 3 Sonnet","kind":"model","provider":"Anthropic","modelId":"claude-3-sonnet-20240229","aliases":["claude-3-sonnet-20240229"],"born":"2024-03-04","died":"2025-07-21","retirementScheduled":null,"causeOfDeath":"superseded","successor":"claude-3-5-sonnet","epitaph":"The middle Claude 3, and the one that was free on claude.ai — so through 2024, to everyone who had never held an API key, Claude meant this. Its model ID ends in 20240229, a leap day it shares with Opus and that neither of them was released on.","url":"https://models.rip/claude-3-sonnet/epitaph","sources":["https://platform.claude.com/docs/en/about-claude/model-deprecations","https://www.anthropic.com/news/claude-3-family"]},{"slug":"text-bison","name":"PaLM 2 for Text","kind":"model","provider":"Google","modelId":"text-bison","aliases":[],"born":"2023-05-11","died":"2025-04-21","retirementScheduled":null,"causeOfDeath":"superseded","successor":"gemini-1.0-pro","epitaph":"Google's first public answer to GPT-4, and for much of 2023 the model behind Bard. It reached developers under an internal size codename — bison, sitting between gecko and unicorn — that escaped into the public API and was never explained. Every PaLM-era endpoint was switched off together on a single day in April 2025.","url":"https://models.rip/text-bison/epitaph","sources":["https://docs.cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versioning","https://cloud.google.com/blog/products/ai-machine-learning/google-cloud-launches-new-ai-models-opens-generative-ai-studio"]},{"slug":"gemini-1.0-pro","name":"Gemini 1.0 Pro","kind":"model","provider":"Google","modelId":"gemini-1.0-pro-001","aliases":["gemini-1.0-pro-001"],"born":"2024-02-15","died":"2025-04-21","retirementScheduled":null,"causeOfDeath":"superseded","successor":"gemini-1.5-pro","epitaph":"The stable snapshot of the model that put Google back in the argument — the one Bard was rebuilt on, and the one every \"Gemini versus GPT-4\" post of early 2024 was really about. It was retired on the same day as the PaLM endpoints it had replaced, fourteen months after it stabilised.","url":"https://models.rip/gemini-1.0-pro/epitaph","sources":["https://docs.cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versioning","https://blog.google/technology/ai/google-gemini-ai/"]},{"slug":"gemini-1.5-pro","name":"Gemini 1.5 Pro","kind":"model","provider":"Google","modelId":"gemini-1.5-pro-001","aliases":["gemini-1.5-pro-001","gemini-1.5-pro-002"],"born":"2024-05-24","died":"2025-09-24","retirementScheduled":null,"causeOfDeath":"superseded","successor":"gemini-2.0-flash","epitaph":"It could take a million tokens, which in 2024 meant an hour of video or an entire repository in one request, and it made a serious case that retrieval was a workaround rather than an architecture. Google gave each of its two snapshots exactly twelve months and switched both off on the anniversary of their release, to the day. The second outlived the first by four months.","url":"https://models.rip/gemini-1.5-pro/epitaph","sources":["https://web.archive.org/web/20250614102734/https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/1-5-pro","https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/"]},{"slug":"gemini-1.5-flash","name":"Gemini 1.5 Flash","kind":"model","provider":"Google","modelId":"gemini-1.5-flash-001","aliases":["gemini-1.5-flash-001","gemini-1.5-flash-002"],"born":"2024-05-24","died":"2025-09-24","retirementScheduled":null,"causeOfDeath":"superseded","successor":"gemini-2.0-flash","epitaph":"Gemini 1.5 Pro proved that a million-token window was possible; Flash was distilled out of it and proved the window could also be cheap, which is the half of the argument that changed what people actually built. The two share a release date and a retirement date, and only one of them was ever priced to be used at volume.","url":"https://models.rip/gemini-1.5-flash/epitaph","sources":["https://web.archive.org/web/20250514231416/https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/1-5-flash","https://blog.google/technology/developers/gemini-gemma-developer-updates-may-2024/"]},{"slug":"gemini-2.0-flash","name":"Gemini 2.0 Flash","kind":"model","provider":"Google","modelId":"gemini-2.0-flash","aliases":[],"born":"2025-02-05","died":"2026-06-01","retirementScheduled":null,"causeOfDeath":"superseded","successor":null,"epitaph":"For sixteen months this was what you got when you called Google's API without thinking hard about it: a million tokens of context, native tool use, and a price low enough that most projects never looked any further. Its retirement closed the whole 2.0 line in one day, taking with it the Flash-Lite that had arrived three weeks behind it.","url":"https://models.rip/gemini-2.0-flash/epitaph","sources":["https://ai.google.dev/gemini-api/docs/deprecations","https://docs.cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versioning"]},{"slug":"mistral-medium-1","name":"Mistral Medium 1.0","kind":"model","provider":"Mistral AI","modelId":"mistral-medium-2312","aliases":["mistral-medium-2312"],"born":"2023-12-11","died":"2025-06-16","retirementScheduled":null,"causeOfDeath":"superseded","successor":"mistral-large-1","epitaph":"The first Mistral model with no weights behind it, from the lab whose reputation was built on giving them away — the launch announcement called it a prototype, and it carried production traffic for eighteen months anyway. It scored 8.6 on MT-Bench against the 8.3 and 7.6 of the two open endpoints it launched beside, and it was retired without ever having been released.","url":"https://models.rip/mistral-medium-1/epitaph","sources":["https://docs.mistral.ai/getting-started/models/models_overview/","https://mistral.ai/news/la-plateforme"]},{"slug":"open-mixtral-8x7b","name":"Mixtral 8x7B","kind":"model","provider":"Mistral AI","modelId":"open-mixtral-8x7b","aliases":[],"born":"2023-12-11","died":"2025-03-30","retirementScheduled":null,"causeOfDeath":"superseded","successor":null,"epitaph":"A sparse mixture of experts that held its own against far larger models while using only a fraction of its parameters on any given token, and that arrived as a torrent link before anyone had written it up. Mistral's endpoint for it closed; the weights did not. It is the one grave here with something still living in it.","url":"https://models.rip/open-mixtral-8x7b/epitaph","sources":["https://docs.mistral.ai/getting-started/models/models_overview/","https://mistral.ai/news/mixtral-of-experts","https://venturebeat.com/business/mistral-ai-bucks-release-trend-by-dropping-torrent-link-to-new-open-source-llm/"]}],"license":"CC BY 4.0 — use it, credit it.","documentation":"https://models.rip/docs"}