Aider

• Support for GPT 4.1, mini and nano.

• Improved support for using architect mode with Gemini 2.5 Pro.

• Add support for xai/grok-3-beta, xai/grok-3-mini-beta, openrouter/x-ai/grok-3-beta, openrouter/x-ai/grok-3-mini-beta, and openrouter/openrouter/optimus-alpha models.

• Added support for grok-3-fast-beta and grok-3-mini-fast-beta models.

• Added new patch edit format for OpenAI's GPT-4.1 model.

• Added new editor-diff, editor-whole, and editor-diff-fenced edit formats.

• Bugfix for automatically selecting the best edit format to use in architect mode.

• Add alias "grok3" for xai/grok-3-beta.

• Add alias "optimus" for openrouter/openrouter/optimus-alpha.

• Fix URL extraction from error messages.

• Allow adding files by full path even if a file with the same basename is already in the chat.

• Fix quoting of values containing '#' in the sample aider.conf.yml.

• Add support for Fireworks AI model 'deepseek-v3-0324', by Felix Lisczyk.

• Aider wrote 92% of the code in this release.

• Added support for the openrouter/openrouter/quasar-alpha model.

  • Currently free on OpenRouter.
  • Quasar scored 55% on the polyglot coding benchmark
  • Run with aider --model quasar

• Offer OpenRouter OAuth authentication if an OpenRouter model is specified but the API key is missing.

• Prevent retrying API calls when the provider reports insufficient credits.

• Improve URL detection to exclude trailing double quotes.

• Bumped deps to pickup litellm change to properly display the root cause of OpenRouter "choices" errors.

• Improve error message for OpenRouter API connection issues to mention potential rate limiting or upstream provider issues.

• Configure weak models (gemini/gemini-2.0-flash and openrouter/google/gemini-2.0-flash-exp:free) for Gemini 2.5 Pro models.

• Add model metadata for openrouter/google/gemini-2.0-flash-exp:free.

• Updated deps for yanked fsspec and aiohttp packages #3699

• Removed redundant dependency check during OpenRouter OAuth flow, by Claudia Pellegrino.

• Aider wrote 86% of the code in this release.

https://aider.chat/HISTORY.html

• OpenRouter OAuth integration:
  • Offer to OAuth against OpenRouter if no model and keys are provided.
  • Select OpenRouter default model based on free/paid tier status if OPENROUTER_API_KEY is set and no model is specified.
• Prioritize gemini/gemini-2.5-pro-exp-03-25 if GEMINI_API_KEY is set, and vertex_ai/gemini-2.5-pro-exp-03-25 if VERTEXAI_PROJECT is set, when no model is specified.
• Validate user-configured color settings on startup and warn/disable invalid ones.
• Warn at startup if --stream and --cache-prompts are used together, as cost estimates may be inaccurate.
• Boost repomap ranking for files whose path components match identifiers mentioned in the chat.
• Change web scraping timeout from an error to a warning, allowing scraping to continue with potentially incomplete content.
• Left-align markdown headings in the terminal output, by Peter Schilling.
• Update edit format to the new model's default when switching models with /model, if the user was using the old model's default format.
• Add the openrouter/deepseek-chat-v3-0324:free model.
• Add Ctrl-X Ctrl-E keybinding to edit the current input buffer in an external editor, by Matteo Landi.

• Added support for SOTA Gemini 2.5 Pro.
• Added support for DeepSeek V3 0324.
• Added a new /context command that automatically identifies which files need to be edited for a given request.
• Added /edit as an alias for the /editor command.
• Added "overeager" mode for Claude 3.7 Sonnet models to try and keep it working within the requested scope.
• Aider wrote 65% of the code in this release.

• Added support for thinking tokens for OpenRouter Sonnet 3.7.
• Added commands to switch between model types: /editor-model for Editor Model, and /weak-model for Weak Model, by csala.
• Added model setting validation to ignore --reasoning-effort and --thinking-tokens if the model doesn't support them.
• Added --check-model-accepts-settings flag (default: true) to force unsupported model settings.
• Annotated which models support reasoning_effort and thinking_tokens settings in the model settings data.
• Improved code block rendering in markdown output with better padding using NoInsetMarkdown.
• Added --git-commit-verify flag (default: False) to control whether git commit hooks are bypassed.
• Fixed autocompletion for /ask, /code, and /architect commands, by shladnik.
• Added vi-like behavior when pressing enter in multiline-mode while in vi normal/navigation-mode, by Marco Mayer.
• Added AWS_PROFILE support for Bedrock models, allowing use of AWS profiles instead of explicit credentials, by lentil32.
• Enhanced --aiderignore argument to resolve both absolute and relative paths, by mopemope.