> ## Documentation Index
> Fetch the complete documentation index at: https://openai-hd4n6.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

### April, 2025

<Update label="Apr 14" tags={["Feature"]}>
  * Added [`gpt-4.1`](/docs/models/gpt-4.1), [`gpt-4.1-mini`](/docs/models/gpt-4.1-mini), and [`gpt-4.1-nano`](/docs/models/gpt-4.1-nano) models to the API. These new models feature improved instruction following, coding, and a larger context window (up to 1M tokens). Announced deprecation of `gpt-4.5-preview`.
</Update>

### March, 2025

<Update label="Mar 20" tags={["Feature"]}>
  * Added `gpt-4o-mini-tts`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `whisper-1` models to the Audio API.
</Update>

<Update label="Mar 19" tags={["Feature"]}>
  * Released [o1-pro](/docs/models/o1-pro), a version of the [o1](/docs/models/o1) reasoning model that uses more compute to answer hard problems with better reasoning and consistency.
</Update>

<Update label="Mar 11" tags={["Feature"]}>
  * Released several new models and tools and a new API for agentic workflows:
  * Released the [Responses API](/docs/guides/responses-vs-chat-completions), a new API for creating and using agents and tools.
  * Released a set of built-in tools for the Responses API: [web search](/docs/guides/tools-web-search), [file search](/docs/guides/tools-file-search), and [computer use](/docs/guides/tools-computer-use).
  * Released the [Agents SDK](/docs/guides/agents), an orchestration framework for designing, building, and deploying agents.
  * Announced new models: `gpt-4o-search-preview`, `gpt-4o-mini-search-preview`, `computer-use-preview`.
  * Announced plans to bring all [Assistants API](/docs/assistants) features to the easier to use [Responses API](/docs/guides/responses-vs-chat-completions), with an anticipated sunset date for Assistants in 2026 (after achieving full feature parity).
</Update>

<Update label="Mar 03" tags={["Update"]}>
  * Added `metadata` field support to fine-tuning jobs.
</Update>

### February, 2025

<Update label="Feb 27" tags={["Update"]}>
  * Released [GPT-4.5](/docs/models#gpt-4-5), our largest and most capable chat model yet. GPT-4.5's high "EQ" and understanding of user intent make it better at creative tasks and agentic planning.
</Update>

### January, 2025

<Update label="Jan 31" tags={["Feature"]}>
  * Launched [o3-mini](/docs/models#o3-mini), a new small reasoning model that is optimized for science, math, and coding tasks.
</Update>