GitHub deprecates selected Anthropic and OpenAI models from Copilot
GitHub deprecated selected Anthropic and OpenAI models across all Copilot experiences on February 17, 2026. The deprecation affects Copilot Chat, inline edits, ask mode, agent mode, and code completions. Specific model names and transition timelines were not disclosed in the initial announcement.
GitHub has deprecated multiple models from Anthropic and OpenAI across its Copilot suite, effective February 17, 2026.
The deprecation impacts all GitHub Copilot experiences, including Copilot Chat, inline edits, ask mode, agent mode, and code completions. However, GitHub's announcement does not specify which specific models were deprecated or provide a transition timeline for users currently relying on affected versions.
What we know
The deprecation was announced on February 19, 2026, two days after the effective date. The move affects both Anthropic and OpenAI model integrations with GitHub's code completion and AI assistance platform.
GitHub did not provide additional details regarding:
- Names of deprecated models
- Replacement models users should migrate to
- Grace period or sunset dates for deprecated models
- Migration guidance for existing integrations
What this means
GitHub users relying on specific Anthropic or OpenAI models through Copilot need to check GitHub's full changelog for model-specific details. The deprecation suggests either model performance improvements elsewhere in the lineup, licensing changes, or technical reasons for phasing out older versions. Developers should review their Copilot configurations to identify which models they currently use and prepare for potential switching costs or API adjustments.
Related Articles
OpenAI Python SDK 3.46.0 adds GPT-6 Rosalind to model catalog and Australia, India, Japan residency options
OpenAI released version 3.46.0 of its Python SDK on 2026-11-05. The update adds GPT-6 Rosalind to the model catalog, introduces Australia, India, and Japan residency options, and adds new image output controls.
METR report: Anthropic's unreleased Model 4 scores 178.6 on AECI, ahead of Opus 5.5
METR's new report discloses three unreleased Anthropic models, Model 2, Model 3 and Model 4. Model 4 scores 178.6 on Anthropic's AECI index, about 3.9 points above Opus 5.5. Anthropic co-founder Sam McCandlish confirmed the report's main findings but said much information was removed.
METR Report: Anthropic's AI Development Pace May Have Doubled Due to Internal AI Use
A new report from AI research nonprofit METR says AI use within Anthropic may have doubled the company's pace of AI development. The rate at which Anthropic's models are improving as of October is roughly twice the rate between March 2024 and October 2025, according to The Information.
Anthropic launches Personal Finance in Claude with read-only Plaid access for US Pro, Max and Ultra users
Anthropic announced Personal Finance in Claude, a feature that connects bank and credit card accounts through Plaid with read-only access. Conversations in the Personal Finance hub are not used to train Anthropic's models. It is available only to Pro, Max and Ultra subscribers in the US.
Comments
Loading...