OpenAI Python SDK v3.10.0 Adds Support for GPT Image 2.5 and API Key Expiration Fields
OpenAI released v3.10.0 of its official Python SDK, adding support for GPT Image 2.5 models and image generation options, plus new expiration fields for service-account API keys. The release does not include pricing, benchmark, or model card details.
OpenAI Ships Python SDK v3.10.0 With GPT Image 2.5 Support
OpenAI released version 3.10.0 of its official Python client library on September 8, 2026, adding programmatic support for GPT Image 2.5 models and new image generation options, according to the release notes published on GitHub.
The update also introduces expiration fields for service-account API keys, giving developers a way to set and track when service-account credentials expire.
What Changed
The release notes list two feature additions:
- GPT Image 2.5 support: The SDK now exposes GPT Image 2.5 models and associated image generation options through the
apimodule, per pull request #3824. No further technical detail — such as resolution limits, pricing, or benchmark scores — is included in the release notes. - Service-account API key expiration fields: Pull request #3802 adds fields that let developers see and manage expiration dates on service-account API keys, a change aimed at credential lifecycle management rather than model behavior.
This is a client library changelog, not a model announcement. OpenAI has not published a separate model card, pricing sheet, or benchmark results for GPT Image 2.5 alongside this SDK release. The full technical specification of GPT Image 2.5 — including context handling for image inputs, output formats, and cost per generation — remains undisclosed in the material reviewed for this release.
Confirmed vs. Unconfirmed
Confirmed: the SDK version bump to 3.10.0, the addition of GPT Image 2.5-related API bindings, and new service-account key expiration fields.
Unconfirmed: any performance claims, pricing, or capability details for GPT Image 2.5 itself, since none appear in this changelog. Readers should treat GPT Image 2.5 as a model that now has client-side plumbing in the Python SDK, not as a model with a documented public specification as of this release.
What This Means
SDK updates like this typically precede or accompany broader model rollouts — adding client bindings is often the first visible signal that a new model is moving toward general availability. The appearance of GPT Image 2.5 in the openai-python library suggests OpenAI is preparing to expose the model more broadly via the API, but until OpenAI publishes pricing, a model card, or benchmark data, developers should treat this as infrastructure groundwork rather than a full product launch. The service-account expiration fields are a smaller, operational change aimed at enterprise credential management rather than model capability.
Related Articles
OpenAI Launches GPT-Image 2.5 With Two New API Models: Sunburst and Flare
OpenAI has released ChatGPT Images 2.5, introducing two new API model IDs — gpt-image-2.5-sunburst and gpt-image-2.5-flare — with improved multi-turn instruction following and better preservation of subjects from reference photos. OpenAI says its image models have now generated more than 3 billion images across ChatGPT and the API.
OpenAI Launches ChatGPT Images 2.5, Cuts Generation Latency by Up to 50%
OpenAI has released ChatGPT Images 2.5, an upgrade to its image generation system that cuts latency by up to 50% compared to Images 2.0 and improves multi-turn editing accuracy. The company also launched two API-accessible models, GPT-Image-2.5 Flare and Sunburst, for developers.
Vercel AI SDK Patches OpenAI Provider to v4.0.60, Adds GPT-6 Reasoning Config Fields
Vercel released @ai-sdk/openai version 4.0.60, a patch update that adds reasoning configuration support referencing 'GPT-6' in the codebase. OpenAI has not announced a GPT-6 model, making this an early SDK-side scaffolding change rather than confirmation of a new release.
OpenAI Publishes GPT-6 Astra Prompting Guide With Banned 'Slop Words' List
OpenAI has published detailed prompting guidance for GPT-6 Astra, addressing the model's tendency to over-clarify, over-test, and use clichéd AI phrasing. The documentation includes specific prompts to encourage more autonomous action and a blocklist of banned words and phrases.
Comments
Loading...