22 tracked changes to OpenAI models in the twelve months to 2026-09-24, newest first. Each one cites OpenAI's own announcement and carries one recommended action.
These are the ids and API surfaces OpenAI named in the announcements we track. They are what the entries below are about, and they are not a claim about everything OpenAI ships.
OpenAI released GPT-6 Astra, which it describes as its most capable model for end to end work, covering reasoning, coding, computer use and tools. It is available in the Responses API and the Chat Completions API.
Agent: A different model plans and calls tools differently. Future AGI describes scoring an agent at four resolutions, end to end, trajectory, step and turn, and writes that a high end to end score can hide bad tool calls, while strong per step scores can still miss that the agent pursued the wrong goal.
Chat assistant: Running the assistant on the new model beside the one you serve is pairwise comparison, one of the four evaluator types LangSmith documents, alongside human review, rule based code functions and LLM as judge.
Summarisation: If a model from this family also runs as your judge, the scoring side is checked against human labels before its verdicts carry weight. Arize writes that a 75 to 90 percent match between judge labels and human labels indicates strong alignment and readiness to scale.
Rerun the suiteAdd gpt-6-astra as a second model in your next scheduled suite run alongside the one you serve today, and read the differences before changing any default.
OpenAI wrote that a rapid increase in traffic can now return a 429 error with the slow_down code, and that temporary overload can return a 503 error with the server_is_overloaded code.
Rerun the suiteCheck that your client and your eval harness treat these two codes as a signal to back off rather than as failures, then run a batch large enough to exercise that path.
OpenAI announced on August 26, 2026 that whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe and gpt-4o-transcribe-diarize are scheduled to shut down on February 26, 2027. The recommended replacements are gpt-live-transcribe and gpt-transcribe.
Summarisation: Arize Phoenix writes that end to end evaluation only inspects the two endpoints, the input and the final output, and that the interesting failures happen in the middle. A transcript sits in that middle, so a summary scored only on its final text does not show which step changed.
Plan a migrationFind every call to one of the four ids, run a held out set of recordings through gpt-transcribe or gpt-live-transcribe, and keep both transcripts so the step after them can be compared before February 26, 2027.
OpenAI reduced GPT-5.6 Sol pricing to $4 per million input tokens and $20 per million output tokens. The entry states the reduced price is promotional through November 21.
Rerun the suiteUpdate the per token rates in your cost model and dashboards, and put the stated promotional end date in the budget calendar.
OpenAI states that Fast mode now supports long context requests exceeding 272K tokens for the GPT-5.6 models.
RAG: Dropping the chunking you added for the old ceiling changes what sits in the context window. Ragas defines faithfulness as the share of claims in a response that can be inferred from the retrieved context, so the score moves with the context as well as with the model.
Summarisation: Summarising a whole document rather than a set of chunks changes the expected output for every case. Galtea warns against updating ground truth to match model behaviour.
Rerun the suiteIf you split long inputs to stay under the old ceiling, run a long document case end to end before removing that chunking.
OpenAI introduced Fast mode, which it describes as up to 2.5 times faster at twice the price. The entry also states that GPT-5.6 Luna costs 80 percent less and GPT-5.6 Terra 20 percent less.
Rerun the suitePrice the three GPT-5.6 tiers against your current spend per request, then run the cheaper tier through your suite before moving any traffic to it.
OpenAI updated the chat-latest snapshot to point to the latest Instant model in ChatGPT.
Chat assistant: An alias that is repointed changes the model behind the assistant with no deploy on your side. Google documents the same mechanism for Gemini, where a latest alias points at the most recent release of a model variation and is hot swapped with every new release.
Generation: Future AGI recommends refreshing a golden dataset immediately after a model update, monthly by default and weekly during rapid change, sampling 200-500 recent production traces stratified by intent and persona.
Re-pin the versionReplace any chat-latest alias in production with a dated snapshot id, so a future repoint does not change behaviour without a deploy.
OpenAI announced the deprecation of reusable prompt objects, the Evals platform and Agent Builder. The v1/prompts API and reusable prompt objects, the Evals dashboard and API, and Agent Builder are scheduled to shut down on November 30, 2026, and existing evals become read only on October 31, 2026. OpenAI says to move reusable prompt content into your application code, and points to the Agents SDK, ChatGPT Workspace Agents and Promptfoo.
Plan a migrationList every place that loads a prompt by id from v1/prompts or runs a job on the Evals platform, and put the move into application code or another runner on the calendar before October 31, 2026.
OpenAI wrote that for organizations without ZDR, its zero data retention setting, prompt_cache_retention now defaults to 24h instead of in_memory.
Rerun the suiteCheck whether your requests set prompt_cache_retention explicitly, and decide whether the new default is the one you want before your next run.
OpenAI released GPT-5.5 as a frontier model with a 1M token context window, structured outputs and extended prompt caching, alongside gpt-5.5-pro.
Extraction: Structured outputs decide whether extracted fields validate against your schema. DeepEval defines a golden as an input plus the expected result, which becomes a full test case once the application produces the actual output, so the same goldens rerun against the new model.
RAG: A larger window invites more retrieved text into the prompt. Ragas defines faithfulness as the share of claims in a response that can be inferred from the retrieved context, and it scores grounding in that context rather than factual truth.
Rerun the suiteRun your structured output cases against gpt-5.5 and check that responses still validate against your schemas before changing the model you serve.
OpenAI released GPT-5.4 mini and GPT-5.4 nano to the Chat Completions and Responses APIs.
Classification: Weights & Biases documents an evaluation as a dataset of test examples plus one or more scoring functions, used to measure performance against repeatable test cases, compare changes over time and identify regressions. That is the structure a move to a smaller id is judged on.
Rerun the suiteIf you are considering a cheaper id for routing or tagging, run the same labelled set through gpt-5.4-mini and gpt-5.4-nano and compare it against the model you use today.
OpenAI wrote that it updated its image encoder to fix a small bug with input_image inputs in gpt-5.4. OpenAI describes it as a bug fix and publishes no new model id alongside it.
Rerun the suiteIf a feature sends images to gpt-5.4, run your image cases again after this date and keep both sets of outputs, because the id you call did not change.
OpenAI released GPT-5.4 as a frontier model with a 1M token context window, tool search, computer use and compaction, alongside gpt-5.4-pro.
Agent: Tool search and computer use add steps that the final answer never shows. Arize Phoenix reconstructs tool_path, the ordered tool calls with their arguments, and tool_io, what each tool was called with and what it returned, and warns that a correct looking answer can come from a broken path.
RAG: Compaction changes what the model still has in front of it when it answers. Ragas defines faithfulness as the share of claims in a response that can be inferred from the retrieved context, so a compacted context is a different thing to be faithful to.
Rerun the suiteRun one long input case against gpt-5.4 before you rely on the larger window, and check how compaction changes what the model still has in front of it.
OpenAI released gpt-5.3-codex to the Responses API. The same entry added the phase parameter, which OpenAI says labels an assistant message as intermediate commentary or final answer.
Agent: Future AGI describes scoring an agent at four resolutions, end to end, trajectory, step and turn, writes that a high end to end score can hide bad tool calls, and warns that strong per step scores can still miss that the agent pursued the wrong goal. A label that separates intermediate commentary from the final answer is read at those resolutions.
Rerun the suiteRun your agent cases against gpt-5.3-codex, and decide whether your harness should record the phase label so intermediate messages stop being scored as answers.
OpenAI launched server side compaction in the Responses API, launched Skills support across local and hosted execution, and released the Hosted Shell tool with support for networking in containers.
Agent: Arize Phoenix writes that end to end evaluation only inspects the two endpoints, the input and the final output, and that the interesting failures happen in the middle where they cannot be seen, naming reasoning, tool selection and decision path. Compaction and a new hosted tool both sit in that middle.
Rerun the suiteIf you turn on server side compaction or adopt the Hosted Shell tool, run a long session case with the spans recorded rather than only the final answer.
OpenAI released gpt-5.2-codex to the Responses API and describes it as optimized for agentic coding tasks in Codex.
Agent: Arize Phoenix describes reconstructing tool_path, the ordered tool calls with their arguments, and tool_io, what each tool was called with and what it returned, and warns that a correct looking answer can come from a broken path. Those are the signals a coding agent is read on.
Rerun the suiteIf a coding or agent feature sits on a pinned Codex id, run your trajectory cases against gpt-5.2-codex before you point anything at it.
OpenAI released GPT-5.2 as its flagship model, stating improvements in reasoning, vision, code generation and spreadsheet understanding, alongside gpt-5.2-chat-latest. The same day OpenAI released client side compaction for long running conversations.
Extraction: Vision and spreadsheet inputs are where extracted fields come from. DeepEval defines a golden as an input plus the expected result, which becomes a full test case once the application produces the actual output, so the document fixtures rerun unchanged against the new model.
Generation: Running the new flagship beside the snapshot you pin is pairwise comparison of two application versions, one of the four evaluator types LangSmith documents.
Rerun the suiteRun your suite against gpt-5.2 alongside the GPT-5.1 snapshot you pin, and pay attention to the vision and document cases the entry calls out.
OpenAI announced the deprecation of the chatgpt-4o-latest snapshot on November 18, 2025, with a shutdown date of February 17, 2026. The recommended replacement is gpt-5.1-chat-latest.
Chat assistant: How much warning a snapshot gets depends on its class. OpenAI says it gives at least 6 months' notice before retiring a generally available model, at least 3 months for specialized variants, and that preview models may be retired with much shorter notice, such as 2 weeks, with no minimum committed.
Generation: Prompts tuned against the old snapshot produce different text on the replacement. Galtea warns against updating ground truth to match model behaviour.
Plan a migrationSearch your configuration for chatgpt-4o-latest and move those calls to gpt-5.1-chat-latest, then rerun the prompts that were tuned for the old snapshot.
OpenAI released GPT-5.1 as a flagship model optimized for steerability, code generation and agentic workflows, and released gpt-5.1-codex and gpt-5.1-codex-mini to the Responses API. The same day OpenAI launched extended prompt cache retention of up to 24 hours.
Agent: Agentic workflows are judged across the whole run. Future AGI writes that agent traces in contemporary frameworks are routinely 15-40 spans deep, naming the OpenAI Agents SDK, LangGraph, CrewAI, AutoGen and Google ADK.
Chat assistant: A family alias resolves to whatever the provider points it at. Google documents this for Gemini, where a latest alias points at the most recent release of a model variation and is hot swapped with every new release, which is the reason to pin an explicit id.
Re-pin the versionPin the exact GPT-5.1 id you intend to serve rather than a family alias, and rerun the prompts you had tuned against GPT-5 before switching.
OpenAI released GPT-5 Pro, which it describes as a version of GPT-5 that uses more compute to think harder. The same DevDay entry launched the v1/videos API with the Sora 2 and Sora 2 Pro models, and released GPT-Realtime mini, gpt-audio-mini and gpt-image-1-mini for cost efficient speech and image work. It also launched Agent Builder, ChatKit and Trace Evals.
Generation: A release that adds generation models gives a team a new option rather than a forced change. Galtea warns against updating ground truth to match model behaviour, so the outputs you already recorded stay the comparison point when a new id is tried.
Rerun the suiteNothing moves until you adopt one of these ids. If you plan to try gpt-5-pro, run your standing prompt set against it first and keep the current model's outputs beside it.
OpenAI announced on September 26, 2025 the deprecation of gpt-3.5-turbo-instruct, babbage-002, davinci-002 and gpt-3.5-turbo-1106, with a shutdown date of September 28, 2026. The listed migration target is gpt-5.6-terra.
Classification: Older ids tend to sit in batch jobs and internal classifiers that nobody watches. OpenAI says it gives at least 6 months' notice before retiring a generally available model, at least 3 months for specialized variants, and that preview models may be retired with much shorter notice, such as 2 weeks, with no minimum committed.
Extraction: Moving an extractor onto a current model is a release like any other. Galtea recommends a tiered release gate in which blocking failures such as safety or policy violations block a deploy at any rate, while regressions gate on the change in fail rate.
Plan a migrationCheck batch jobs and older internal tools for these four ids ahead of the stated shutdown date, and move any remaining traffic to a current model.
Change-log entries restate provider announcements with sources and dates. Impact notes cite public practitioner reports. The site publishes no measurements of its own on any model.
Questions about OpenAI changes
Where do the OpenAI entries come from?
From OpenAI's own pages. Every entry links to the changelog, release note, deprecation table or pricing page that carries the announcement. Nothing here is sourced from coverage or from reports by users.
Does DriftCaught test OpenAI models?
No. This site publishes no measurement of any model. We restate what the provider announced and cite published practitioner guides for what that kind of change typically touches.
What should I do when OpenAI announces something?
Check whether the model id you run is named. If it is, rerun your suite against your dataset and read the result against the thresholds you agreed. Each entry carries one recommended action: rerun, re-pin, re-prompt or migrate.
Is every OpenAI announcement here?
No. The log covers changes to the model families we track for customers, inside a twelve-month window, where the announcement is reachable on OpenAI's own domain. Send us a link to anything missing and we will add it.