Added support for all GPT-5 models. · Added support for Grok-4 via `xai/grok-4` and `openrouter/x-ai/grok-4` model names. · Added support for `gemini/gemini-2.5-flash-lite-preview-06-17` model, by Tamir Zahavi-Brunner. · `/clear` now prints “All chat history cleared.” so you know it worked, by Zexin Yuan. · `/undo` output now shows only the first line of each commit message, making it easier to read.

Primary source ↗

Aiderv0.85.06/27/2025, 11:47:09 PM

v0.85.0 Aider v0.85.0

Added support for new Gemini models including `gemini-2.5-pro`, `gemini-2.5-flash`, and `gemini-2.5-pro-preview-06-05` with thinking tokens support. · Updated model aliases: `flash` now points to `gemini-2.5-flash` and `gemini` now points to `gemini-2.5-pro`. · Support for Responses API models like o1-pro, o3-pro. · Added support for OpenAI o3-pro model across multiple providers. · Enhanced thinking tokens support: can now be disabled by setting to 0, and improved help text with examples.

Primary source ↗

Aiderv0.84.05/30/2025, 11:28:11 PM

v0.84.0 Aider v0.84.0

Added support for new Claude models including the Sonnet 4 and Opus 4 series (e.g., `claude-sonnet-4-20250514`, · Added support for the `vertex_ai/gemini-2.5-flash-preview-05-20` model. · Updated default OpenRouter models during onboarding to `deepseek/deepseek-r1:free` for the free tier and · Automatically refresh GitHub Copilot tokens when used as OpenAI API keys, by Lih Chen. · Fixed an issue where files explicitly added via the command line were not correctly ignored if listed in `.gitignore

Primary source ↗

Aiderv0.83.05/9/2025, 10:46:05 PM

v0.83.0 Aider v0.83.0

Added support for `gemini-2.5-pro-preview-05-06` models. · Added support for `qwen3-235b` models. · Added repo-map support for OCaml and OCaml interface files, by Andrey Popp. · Added a spinner animation while waiting for the LLM to start streaming its response. · Updated the spinner animation to a Knight Rider style.

Primary source ↗

Aiderv0.82.04/14/2025, 11:29:05 PM

v0.82.0 Aider v0.82.0

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`, · 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.

Primary source ↗

Aiderv0.81.04/4/2025, 9:06:20 AM

v0.81.0 Aider v0.81.0

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.

Primary source ↗

Aiderv0.80.03/31/2025, 1:21:50 AM

v0.80.0 Aider v0.80.0

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.

Primary source ↗

Aiderv0.79.03/25/2025, 9:16:38 PM

v0.79.0 Aider v0.79.0

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.

Primary source ↗

Aiderv0.78.03/21/2025, 6:59:35 PM

v0.78.0 Aider v0.78.0

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

Primary source ↗

Aiderv0.77.03/13/2025, 9:46:58 PM

v0.77.0 Aider v0.77.0

Big upgrade in [programming languages supported](https://aider.chat/docs/languages.html) by adopting [tree-sitter-language-pack](https://github.com/Goldziher/tree-sitter-language-pack/). · 130 new languages with linter support. · 20 new languages with repo-map support. · Added `/think-tokens` command to set thinking token budget with support for human-readable formats (8k, 10.5k, 0.5M). · Added `/reasoning-effort` command to control model reasoning level.

Primary source ↗

Aiderv0.76.03/10/2025, 4:00:08 PM

v0.76.0 Aider v0.76.0

Improved support for [thinking/reasoning models](https://aider.chat/docs/config/reasoning.html): · Added `--thinking-tokens` CLI option to control token budget for models that support thinking. · Display thinking/reasoning content from LLMs which return it. · Enhanced handling of reasoning tags to better clean up model responses. · Added deprecation warning for `remove_reasoning` setting, now replaced by `reasoning_tag`.

Primary source ↗

Aiderv0.75.03/4/2025, 8:41:19 PM

v0.75.0 Aider v0.75.0

Basic support for Claude 3.7 Sonnet · Use `--model sonnet` to use the new 3.7 · Thinking support coming soon. · Bugfix to `/editor` command. · Downgrade streamlit dependency to avoid threading bug.

Primary source ↗

Aiderv0.74.02/6/2025, 10:43:06 PM

v0.74.0 Aider v0.74.0

Dynamically changes the Ollama context window to hold the current chat. · Better support for o3-mini, DeepSeek V3 & R1, o1-mini, o1 via secondary API providers. · Remove `<think>` tags from R1 responses for commit messages (and other weak model uses). · Can now specify `use_temperature: <float>` in model settings, not just true/false. · The full docker container now includes `boto3` for Bedrock.

Primary source ↗

Aiderv0.73.01/31/2025, 10:02:06 PM

v0.73.0 Aider v0.73.0

Full support for o3-mini: `aider --model o3-mini` · New `--reasoning-effort` argument: low, medium, high. · Improved handling of context window size limits, with better messaging and Ollama-specific guidance. · Added support for removing model-specific reasoning tags from responses with `remove_reasoning: tagname` model setting. · Auto-create parent directories when creating new files, by xqyz.

Primary source ↗

Aiderv0.72.01/20/2025, 10:26:59 PM

v0.72.0 Aider v0.72.0

Support for DeepSeek R1. · Use shortcut: `--model r1` · Also via OpenRouter: `--model openrouter/deepseek/deepseek-r1` · Added Kotlin syntax support to repo map, by Paul Walker. · Added `--line-endings` for file writing, by Titusz Pan.

Primary source ↗

Aiderv0.71.01/10/2025, 11:02:26 PM

v0.71.0 Aider v0.71.0

Prompts to help DeepSeek work better when alternating between `/ask` and `/code`. · Streaming pretty LLM responses is smoother and faster for long replies. · Streaming automatically turns of for model that don't support it · Can now switch to/from `/model o1` and a streaming model · Pretty output remains enabled even when editing files with triple-backtick fences

Primary source ↗

Aiderv0.70.012/26/2024, 11:22:53 PM

v0.70.0 Aider v0.70.0

Full support for o1 models. · Watch files now honors `--subtree-only`, and only watches that subtree. · Improved prompting for watch files, to work more reliably with more models. · New install methods via uv, including one-liners. · Support for openrouter/deepseek/deepseek-chat model.

Primary source ↗

Aiderv0.69.012/13/2024, 7:45:41 PM

v0.69.0 Aider v0.69.0

[Watch files](https://aider.chat/docs/usage/watch.html) improvements: · Use `# ... AI?` comments to trigger aider and ask questions about your code. · Now watches *all* files, not just certain source files. · Use `# AI comments`, `// AI comments`, or `-- AI comments` to give aider instructions in any text file. · Full support for Gemini Flash 2.0 Exp:

Primary source ↗

Aiderv0.68.012/10/2024, 4:28:05 PM

v0.68.0 Aider v0.68.0

[Aider works with LLM web chat UIs](https://aider.chat/docs/usage/copypaste.html). · New `--copy-paste` mode. · New `/copy-context` command. · [Set API keys and other environment variables for all providers from command line or yaml conf file](https://aider.chat/docs/config/aider_conf.html#storing-llm-keys). · New `--api-key provider=key` setting.

Primary source ↗

Aiderv0.67.012/6/2024, 2:44:33 PM

v0.67.0 Aider v0.67.0

[Use aider in your IDE or editor](https://aider.chat/docs/usage/watch.html). · Run `aider --watch-files` and it will watch for instructions you add to your source files. · One-liner `# ...` or `// ...` comments that start or end with "AI" are instructions to aider. · When aider sees "AI!" it reads and follows all the instructions in AI comments. · Support for new Amazon Bedrock Nova models.

Primary source ↗

Aiderv0.66.012/1/2024, 5:20:31 PM

v0.66.0 Aider v0.66.0

PDF support for Sonnet and Gemini models. · Added `--voice-input-device` to select audio input device for voice recording, by @preynal. · Added `--timeout` option to configure API call timeouts. · Set cwd to repo root when running shell commands. · Added Ctrl-Up/Down keyboard shortcuts for per-message history navigation.

Primary source ↗

Aiderv0.65.011/26/2024, 10:07:50 PM

v0.65.0 Aider v0.65.0

Added `--alias` config to define [custom model aliases](https://aider.chat/docs/config/model-aliases.html). · Added `--[no-]detect-urls` flag to disable detecting and offering to scrape URLs found in the chat. · Ollama models now default to an 8k context window. · Added [RepoMap support for Dart language](https://aider.chat/docs/languages.html) by @malkoG. · Ask 2.5% of users if they want to opt-in to [analytics](https://aider.chat/docs/more/analytics.html).

Primary source ↗

Aiderv0.64.011/21/2024, 8:47:03 PM

v0.64.0 Aider v0.64.0

Added [`/editor` command](https://aider.chat/docs/usage/commands.html) to open system editor for writing prompts, by @thehunmonkgroup. · Full support for `gpt-4o-2024-11-20`. · Stream o1 models by default. · `/run` and suggested shell commands are less mysterious and now confirm that they "Added XX lines of output to the chat." · Ask 1% of users if they want to opt-in to [analytics](https://aider.chat/docs/more/analytics.html).

Primary source ↗

Aiderv0.63.011/13/2024, 9:38:30 PM

v0.63.0 Aider v0.63.0

Support for Qwen 2.5 Coder 32B. · `/web` command just adds the page to the chat, without triggering an LLM response. · Improved prompting for the user's preferred chat language. · Improved handling of LiteLLM exceptions. · Bugfix for double-counting tokens when reporting cache stats.

Primary source ↗

Aiderv0.62.011/4/2024, 11:41:04 PM

v0.62.0 Aider v0.62.0

Full support for Claude 3.5 Haiku · Scored 75% on [aider's code editing leaderboard](https://aider.chat/docs/leaderboards/). · Almost as good as Sonnet at much lower cost. · Launch with `--haiku` to use it. · Easily apply file edits from ChatGPT, Claude or other web apps

Primary source ↗

Aiderv0.61.011/1/2024, 4:41:01 PM

v0.61.0 Aider v0.61.0

Load and save aider slash-commands to files: · `/save <fname>` command will make a file of `/add` and `/read-only` commands that recreate the current file context in the chat. · `/load <fname>` will replay the commands in the file. · You can use `/load` to run any arbitrary set of slash-commands, not just `/add` and `/read-only`. · Use `--load <fname>` to run a list of commands on launch, before the interactive chat begins.

Primary source ↗

Aiderv0.60.010/22/2024, 9:21:03 PM

v0.60.0

Full support for Sonnet 10/22, the new SOTA model on aider's code editing benchmark. · Aider uses Sonnet 10/22 by default. · Improved formatting of added and read-only files above chat prompt, by @jbellis. · Improved support for o1 models by more flexibly parsing their nonconforming code edit replies. · Corrected diff edit format prompt that only the first match is replaced.

Primary source ↗

Polled sources

[github-releases] GitHub Releases

github_releases · every 180m

https://github.com/Aider-AI/aider/releases

[official-history] Aider release history site

html · every 180m

https://aider.chat/HISTORY.html

[history-md] HISTORY.md

markdown_changelog · every 180m

https://raw.githubusercontent.com/Aider-AI/aider/main/HISTORY.md