Changelog | OpenAI API

April, 2026Apr 23Featuregpt-5.5gpt-5.5-prov1/responsesv1/chat/completionsv1/batchReleased GPT-5.5, a new frontier model for complex professional work, to the Chat Completions and Responses API, and released GPT-5.5 pro for Responses API requests, including through Batch, for tougher problems that benefit from more compute.GPT-5.5 supports a 1M token context window, image input, structured outputs, function calling, prompt caching, Batch, tool search, built-in computer use, hosted shell, apply patch, Skills, MCP, and web search. GPT-5.5 defaults to medium reasoning effort.Apr 21Featuregpt-image-2v1/images/generationsv1/images/editsv1/batchReleased GPT Image 2, a state-of-the-art image generation model for image generation and editing. GPT Image 2 supports flexible image sizes, high-fidelity image inputs, token-based image pricing, and Batch API support with a 50% discount.Apr 15UpdateUpdated the Agents SDK with new capabilities, including: running agents in controlled sandboxes; inspecting and customizing the open-source harness; and controlling when memories are created and where they're stored. March, 2026Mar 17Featuregpt-5.4-minigpt-5.4-nanov1/responsesv1/chat/completionsReleased GPT-5.4 mini and GPT-5.4 nano to the Chat Completions and Responses API. GPT-5.4 mini brings GPT-5.4-class capabilities to a faster, more efficient model for high-volume workloads, while GPT-5.4 nano is optimized for simple high-volume tasks where speed and cost matter most.GPT-5.4 mini supports tool search, built-in computer use, and compaction. GPT-5.4 nano supports compaction, but does not support tool search or computer use.

Mar 16Updategpt-5.3-chat-latestUpdated the gpt-5.3-chat-latest slug to point to the latest model currently used in ChatGPT.Mar 13Fixgpt-5.4v1/responsesv1/chat/completionsUpdated our image encoder to fix a small bug with input_image inputs in GPT-5.4. Some image understanding use cases may now see improved quality. No action is required.Mar 12Featuresora-2sora-2-prov1/videosv1/videos/charactersv1/videos/extensionsv1/batchExpanded the Sora API with reusable character references, longer generations up to 20 seconds, 1080p output for sora-2-pro, video extensions, and Batch API support for POST /v1/videos. 1080p generations on sora-2-pro are billed at $0.70 per second. Learn more here.Mar 12Updatesora-2sora-2-prov1/videos/editsv1/videos/{video_id}/remixAdded POST /v1/videos/edits for editing existing videos. This will replace POST /v1/videos/{video_id}/remix, which will be deprecated in 6 months. Learn more here.Mar 5Featuregpt-5.4gpt-5.4-prov1/responsesv1/chat/completionsReleased GPT-5.4, our newest frontier model for professional work, to the Chat Completions and Responses API, and released GPT-5.4 pro to the Responses API for tougher problems that benefit from more compute.Also released: Tool search in the Responses API, which lets models defer large tool surfaces until runtime to reduce token usage, preserve cache performance, and improve latency. Built-in Computer use support in GPT-5.4 through the Responses API computer tool for screenshot-based UI interaction. A 1M token context window and native Compaction support for longer-running agent workflows. Mar 3Featuregpt-5.3-chat-latestv1/chat/completionsv1/responsesReleased gpt-5.3-chat-latest to the Chat Completions and Responses API. This model points to the GPT-5.3 Instant snapshot currently used in ChatGPT.

Read more here.February, 2026Feb 24Featurev1/responsesv1/chat/completionsExpanded input_file support to accept more document, presentation, spreadsheet, code, and text file types. Learn more here.Feb 24Featurev1/responsesReleased phase to the Responses API. It labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). Read more here.Feb 24Featuregpt-5.3-codexv1/responsesReleased gpt-5.3-codex to the Responses API. Read more here.Feb 23Featurev1/responsesLaunched WebSocket mode for the Responses API. Learn more here.Feb 23Featuregpt-realtime-1.5gpt-audio-1.5v1/realtimev1/chat/completionsReleased gpt-realtime-1.5 to the Realtime API. Read more here.Released gpt-audio-1.5 to the Chat Completions API. Read more here.Feb 10Featuregpt-image-1.5gpt-image-1gpt-image-1-minichatgpt-image-latestv1/batchBatch API is now supported for GPT Image models: gpt-image-1.5, chatgpt-image-latest, gpt-image-1, and gpt-image-1-mini.Feb 10Updategpt-5.2-chat-latestUpdated the gpt-5.2-chat-latest slug to point to the latest model currently used in ChatGPT.Feb 10Feb 10Featurev1/responsesLaunched support for Skills in the Responses API. We support Skills across both local execution and hosted container-based execution.Feb 10Featurev1/responsesLaunched a new Hosted Shell tool, as well as support for networking in containers.Feb 9Featuregpt-image-1.5gpt-image-1gpt-image-1-minichatgpt-image-latestv1/images/editsAdded support for application/json requests on /v1/images/edits for GPT image models. JSON requests use images (and optional mask) with image_url or file_id references instead of multipart uploads.

Feb 3Updategpt-5.2gpt-5.2-codexWe have optimized our inference stack for API customers and GPT-5.2 and GPT-5.2-Codex now run ~40% faster. Model and model weights are unchanged.January, 2026Jan 15AnnouncementAnnounced Open Responses: an open-source spec for building multi-provider, interoperable LLM interfaces built on top of the original OpenAI Responses API.Jan 14Featuregpt-5.2-codexv1/responsesReleased gpt-5.2-codex to the Responses API. GPT-5.2-Codex is a version of GPT-5.2 optimized for agentic coding tasks in Codex or similar environments. Read more here.Jan 13Featurev1/realtimeAdded dedicated SIP IP ranges for Realtime API. sip.api.openai.com does GeoIP routing, and will direct SIP traffic to the closest region. Learn more.Jan 13Updategpt-realtime-minigpt-audio-miniUpdated the gpt-realtime-mini and gpt-audio-mini slugs to point to the 2025-12-15 snapshots. If you need the previous model snapshots, use gpt-realtime-mini-2025-10-06 and gpt-audio-mini-2025-10-06.Jan 13Updatesora-2Updated the sora-2 slug to point to sora-2-2025-12-08. If you need the previous model snapshot, use sora-2-2025-10-06.Jan 13Updategpt-4o-mini-ttsgpt-4o-mini-transcribeUpdated the gpt-4o-mini-tts and gpt-4o-mini-transcribe slugs to point to the 2025-12-15 snapshots. If you need the previous model snapshots, use gpt-4o-mini-tts-2025-03-20 and gpt-4o-mini-transcribe-2025-03-20.

We currently recomend using gpt-4o-mini-transcribe over gpt-4o-transcribe for the best results.Jan 9Fixgpt-image-1.5chatgpt-image-latestFixed an issue where gpt-image-1.5 and chatgpt-image-latest were incorrectly using high fidelity for image edits through /v1/images/edits, even when fidelity was explicitly set to low (the default).December, 2025Dec 19Updategpt-image-1.5chatgpt-image-latestAdded gpt-image-1.5 and chatgpt-image-latest to the Responses API image generation tool.Dec 16Dec 15Featuregpt-realtime-minigpt-audio-minigpt-4o-mini-transcribegpt-4o-mini-ttsReleased four new dated audio snapshots. These updates deliver reliability, quality, and voice fidelity improvements for real-time, voice-driven applications. Read more here. gpt-realtime-mini-2025-12-15 gpt-audio-mini-2025-12-15 gpt-4o-mini-transcribe-2025-12-15 gpt-4o-mini-tts-2025-12-15 This launch also includes support for Custom voices for eligible customers.Dec 11Featuregpt-5.2gpt-5.2-chat-latestv1/responsesv1/chat/completionsReleased GPT-5.2, the newest flagship model in the GPT-5 model family. GPT-5.2 shows improvements over the previous GPT-5.1 in: General intelligence Instruction following Accuracy and token efficiency Multimodality—especially vision Code generation—especially front-end UI creation Tool calling and context management in the API Spreadsheet understanding and creation. What's new in 5.2 is a new xhigh reasoning effort level, concise reasoning summaries, and new context management using compaction.Dec 11Featurev1/responses/compactReleased client-side compaction. For long-running conversations with the Responses API, you can use the /responses/compact endpoint to shrink the context you send with each turn.

Dec 4Featuregpt-5.1-codex-maxv1/responsesReleased gpt-5.1-codex-max to the Responses API. GPT-5.1-Codex is our most intelligent coding model optimized for long-horizon, agentic coding tasks. Read more here.November, 2025Nov 20Featurev1/realtimeAdded support for DTMF key presses in the Realtime API. You can now receive DTMF events while using a Realtime sideband connection. See docs here for more information.Nov 13Featuregpt-5.1gpt-5.1-codexgpt-5.1-chat-latestgpt-5.1-codex-miniv1/responsesv1/chat/completionsReleased GPT-5.1, the newest flagship model in the GPT-5 model family. GPT-5.1 is trained to be especially proficient in: Steerability and faster responses when less thinking's required Code generation and coding use cases Agentic workflows Note that GPT-5.1 defaults to a new none reasoning setting for faster responses when less thinking's required—different from the previous medium default setting in GPT-5.Nov 13Nov 13Featuregpt-5.1-codexgpt-5.1-codex-miniv1/responsesReleased gpt-5.1-codex and gpt-5.1-codex-mini to the Responses API. GPT-5.1-Codex is a version of GPT-5.1 optimized for agentic coding tasks in Codex or similar environments. Read more here.Nov 13FeatureReleased extended prompt cache retention. Extended prompt cache retention keeps cached prefixes active for longer, up to a maximum of 24 hours. Extended Prompt Caching works by offloading the key/value tensors to GPU-local storage when memory is full, significantly increasing the storage capacity available for caching.October, 2025Oct 29Featuregpt-oss-safeguard-120bgpt-oss-safeguard-20bgpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss.

Read more here.Oct 24FeatureReleased Enterprise Key Management (EKM). Enterprise Key Management (EKM) allows you to encrypt your customer content at OpenAI using keys managed by your own external Key Management System (KMS).Oct 24FeatureOct 6Oct 1FeatureReleased IP allowlist. IP allowlisting restricts API access to only the IP addresses or ranges you specify.September, 2025Sep 26Featurev1/responsesAdded support for image and file as a tool call output in Responses API.Sep 23Featuregpt-5-codexv1/responsesLaunched special-purpose model gpt-5-codex, built and optimized for use with the Codex CLI.August, 2025Aug 28Aug 21Featurev1/responsesAdded support for connectors to the Responses API. Connectors are OpenAI-maintained MCP wrappers for popular services like Google apps, Dropbox, and more that can be used to give model read access to data stored in those services.Aug 20Featurev1/conversationsv1/responsesv1/assistantsReleased the Conversations API, which allows you to create and manage long-running conversations with the Responses API. See the migration guide to see a side-by-side comparison and learn how to migrate from an Assistants API integration to Responses and Conversations.Aug 7Featurev1/chat/completionsv1/responsesReleased GPT-5 family of models in the API, including gpt-5, gpt-5-mini, and gpt-5-nano.Introduced the minimal reasoning effort value to optimize for fast responses in GPT-5 models (which support reasoning).Introduced custom tool call type, which allows for freeform inputs to and outputs from the model when tool calling.June, 2025Jun 27FeatureLaunched support for Priority processing. Priority processing delivers significantly lower and more consistent latency compared to Standard processing while keeping pay-as-you-go flexibility.Jun 24Jun 13Featurev1/responsesNew reusable prompts are now available in the dashboard and Responses API. Via API, you can now reference templates created in the dashboard via the prompt parameter (with a prompt id, optional version) and supply dynamic variables that can include strings, images, or file inputs. Reusable prompts are not available in Chat Completions.