Anthropic Python SDK v0.109.2 Removes Retired Models from API
Anthropic released version 0.109.2 of its Python SDK on June 15, 2026, removing retired models from the API and SDK. The update represents a maintenance release focused on cleaning up deprecated model endpoints.
Anthropic Python SDK v0.109.2 Removes Retired Models
Anthropic released version 0.109.2 of its Python SDK on June 15, 2026, removing retired models from the API and SDK. The release represents a cleanup effort to remove deprecated model endpoints.
What Changed
The update includes a single change: the removal of retired models from both the API and SDK codebase. The specific models removed were not detailed in the release notes.
The release includes no new features, bug fixes, or performance improvements beyond this cleanup task.
Version Details
The release jumps from v0.109.1 to v0.109.2, indicating a patch-level update. The commit hash for this release is ebb1715.
Developers using the Anthropic Python SDK should update to ensure their code references only currently supported models. Applications attempting to access removed model endpoints may encounter errors after updating.
What This Means
This is a routine maintenance release that removes deprecated functionality from Anthropic's Python SDK. The removal of retired models suggests Anthropic is actively managing its model lifecycle and cleaning up legacy endpoints. Developers should review their code for references to older models and migrate to current model versions if necessary. The lack of a migration guide in the release notes indicates these were likely models already announced as deprecated in previous communications.
Related Articles
OpenAI Cuts GPT-5.6 Luna Price 80%, Terra 20%, as Enterprise Cost Pressure Mounts
OpenAI is cutting the price of GPT-5.6 Luna by 80% and GPT-5.6 Terra by 20%, just three weeks after launching the models. The move comes as enterprises grow more cost-conscious and rivals including Anthropic, Google, and Moonshot AI push cheaper alternatives.
Anthropic Researchers Use Claude Mythos Preview to Find New Cryptographic Attacks on HAWK and Weakened AES
Anthropic researchers used a Claude model called Mythos Preview to discover new cryptanalytic attacks against the HAWK signature scheme and a weakened version of AES. The work took 60 hours and roughly $100,000 in API costs, with human researchers repeatedly intervening to stop the model from giving up.
Anthropic's Claude Mythos Preview Discovers New Attacks on AES Encryption and Post-Quantum Signature Scheme HAWK
Anthropic's Claude Mythos Preview model independently discovered a new cryptanalytic attack on a reduced version of AES-128 and improved an existing attack on the post-quantum signature scheme HAWK. Each research run cost roughly $100,000 in API fees, with human researchers largely limited to project management and verification.
Amazon Reportedly Scales Back Nova AI Models, Shifts Resources to New Frontier Research Team
Amazon is reportedly scaling back active development of its Nova Premier, Nova Omni, Reel, and Canvas AI models, according to Business Insider. Resources are shifting to a new Frontier Model Research group led by Pieter Abbeel, with a new foundation model reportedly planned for re:Invent this fall.
Comments
Loading...