MiniMax M3.1 Flash is available through the MiniMax API, M Plan and MiniMax Code, with model weights to follow. Listed prices per million tokens are $0.15 for input, $0.60 for output and $0.015 for cached input.
GitHub deprecated Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini and Grok 4.5 across most Copilot experiences on October 19, 2026. Enterprise administrators may need to enable replacement models through model policies.
Claude Code v2.1.304 adds guided auto-mode setup using the project and recent sessions. It also adds a command that compares Managed Agents settings with Anthropic's security guide without changing them.
Cursor cloud agents can now create interactive canvases that users can share by link. The update also introduces a beta Environments API for creating and managing cloud environments, which now support up to 300 repositories.
Claude Code v2.1.302 enables fork subagents by default in the Agent SDK, desktop app and VS Code. It also fixes MCP 2026-07-28 tool failures when resultType, ttlMs or cacheScope is omitted, and reduces filesystem calls when loading plugins.
GitHub's Slack and Teams assistant can now work across multiple repositories in one conversation, including issue creation, code changes and bug investigations. Shared Slack messages and threads can also provide context.
GitHub scheduled Copilot deprecation of Claude Opus 4.8, Claude Opus 5 and GPT-5.6 Terra for November 16, 2026. Claude Opus 4.8 remains available to individual subscribers on annual plans.
Codex 0.163.0 lets follow-up messages steer an active response immediately and can run independent read-only tool calls in parallel. It also adds searchable preferences through the /config interface.
GitHub introduced HydraFusion Max and updated HydraFusion's model pool and orchestration workflows. Both remain research previews in VS Code, the Copilot app and Copilot CLI, available on Pro, Pro+, Business and Enterprise plans with experimental or preview features enabled, subject to organization model policies.