changelogOpenAI

OpenAI Python SDK v3.13.0 Adds Support for New Agents API

TL;DR

OpenAI shipped v3.13.0 of its openai-python library, adding support for a new Agents API. The release is a client-library update, not a new model.

2 min read
0

OpenAI Python SDK v3.13.0 Adds Agents API Support

OpenAI released version 3.13.0 of its official openai-python library on September 10, per the GitHub release tag. The update's sole listed feature is client support for a new Agents API (commit 1c4284a).

What changed

The release notes are minimal, consistent with prior patch-style updates to the SDK:

  • api: add Agents API — the Python client now exposes methods for the Agents API endpoint

No further detail is provided in the changelog about the Agents API's scope, request/response schema, supported models, or pricing. OpenAI has not published accompanying documentation in this release, so the practical capabilities of the endpoint remain according to OpenAI's commit message alone rather than a full specification.

Context

This is a library release, not a model release. The openai-python repository ships incremental updates to the official Python client that wraps OpenAI's REST API — version bumps here typically track new endpoints, bug fixes, or type updates rather than new model weights. Nothing in this release indicates a new foundation model, updated context window, or revised pricing for any OpenAI model.

The versioning jump follows OpenAI's pattern of frequent minor SDK releases (v3.x series), reflecting ongoing expansion of the API surface rather than a single monolithic model update.

What this means

Developers using openai-python can now call an Agents API directly through the official client, once OpenAI publishes matching documentation for the endpoint. Until OpenAI details the Agents API's behavior, supported models, and pricing, teams should treat this as an early access point rather than a production-ready feature. The absence of specifics in the release notes — no context window, no benchmark, no pricing per 1M tokens — means this update is best understood as plumbing: it enables future agent-building workflows in code, but the substance of what an "agent" call actually does on OpenAI's backend has not yet been disclosed.

Comments

Loading...