●Change8

Aider models

Component

Updates related to the models component of Aider.

15 releases89 features40 bug fixesView all Aider releases

All MODELS Features

  • Added support for all GPT-5 models.(v0.86.0)
  • Added support for Grok-4 via model names `xai/grok-4` and `openrouter/x-ai/grok-4`.(v0.86.0)
  • Added support for the `gemini/gemini-2.5-flash-lite-preview-06-17` model.(v0.86.0)
  • Added support for the `openrouter/moonshotai/kimi-k2` model.(v0.86.0)
  • Enabled display of model announcements when using the no-argument `/model` command.(v0.86.0)
  • 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.(v0.85.0)
  • Updated model aliases: 'flash' now points to gemini-2.5-flash and 'gemini' now points to gemini-2.5-pro.(v0.85.0)
  • Added support for Responses API models like o1-pro and o3-pro.(v0.85.0)
  • Added support for OpenAI o3-pro model across multiple providers.(v0.85.0)
  • Enabled adding files listed in .gitignore to Aider's editing scope via the --add-gitignore-files flag.(v0.85.0)
  • Enabled co-authored-by attribution by default for commit messages.(v0.85.0)
  • Added --commit-language option to specify the language for commit messages.(v0.85.0)
  • Added custom PostHog analytics configuration options using --analytics-posthog-host and --analytics-posthog-project-api-key flags.(v0.85.0)
  • Added MATLAB language support for repository maps.(v0.85.0)
  • Added Clojure language support for repository maps.(v0.85.0)
  • Added support for new Claude models including the Sonnet 4 and Opus 4 series across various providers.(v0.84.0)
  • Added support for the Vertex AI Gemini 2.5 Flash preview model.(v0.84.0)
  • Updated default OpenRouter models during onboarding to `deepseek/deepseek-r1:free` for the free tier and `anthropic/claude-sonnet-4` for paid tiers.(v0.84.0)
  • Enabled automatic refreshing of GitHub Copilot tokens when used as OpenAI API keys.(v0.84.0)
  • Added support for `gemini-2.5-pro-preview-05-06` models.(v0.83.0)
  • Added support for `qwen3-235b` models.(v0.83.0)
  • Added repo-map support for OCaml and OCaml interface files.(v0.83.0)
  • Introduced `--attribute-co-authored-by` option to add co-author trailer to commit messages.(v0.83.0)
  • Added tracking of total tokens sent and received to benchmark statistics.(v0.83.0)
  • Automatically fetch model parameters (context window, pricing) for OpenRouter models directly from their website.(v0.83.0)
  • Enabled support for `thinking_tokens` and `reasoning_effort` parameters for OpenRouter models.(v0.83.0)
  • Added model settings for `openrouter/google/gemini-2.5-pro-preview-03-25`.(v0.83.0)
  • Added `--disable-playwright` flag to prevent Playwright installation prompts and usage.(v0.83.0)
  • Enabled `reasoning_effort` for Gemini 2.5 Flash models.(v0.83.0)
  • Added a `--shell-completions` argument to generate shell completion scripts (e.g., for bash, zsh).(v0.83.0)
  • Explicit `--attribute-author` or `--attribute-committer` flags now override the default behavior when `--attribute-co-authored-by` is used.(v0.83.0)
  • Added support for GPT 4.1, mini, and nano models.(v0.82.0)
  • Added support for multiple new models including xai/grok-3-beta, grok-3-fast-beta, and openrouter/openrouter/optimus-alpha variants.(v0.82.0)
  • Added new `patch` edit format for OpenAI's GPT-4.1 model.(v0.82.0)
  • Added new edit formats: `editor-diff`, `editor-whole`, and `editor-diff-fenced`.(v0.82.0)
  • Added alias `grok3` for the `xai/grok-3-beta` model.(v0.82.0)
  • Added alias `optimus` for the `openrouter/openrouter/optimus-alpha` model.(v0.82.0)
  • Enabled adding files by full path even if a file with the same basename already exists in the chat.(v0.82.0)
  • Added support for the new `openrouter/openrouter/quasar-alpha` model, runnable via `aider --model quasar`.(v0.81.0)
  • Enabled OpenRouter OAuth authentication when an OpenRouter model is selected but the API key is missing.(v0.81.0)
  • Added OpenRouter OAuth integration, offering to authenticate if no model or keys are provided.(v0.80.0)
  • Enabled automatic selection of OpenRouter default model based on free/paid tier status when the API key is set but no model is specified.(v0.80.0)
  • Prioritized specific Gemini and Vertex AI experimental models when no model is specified and corresponding keys are set.(v0.80.0)
  • Added the `openrouter/deepseek-chat-v3-0324:free` model.(v0.80.0)
  • Added `Ctrl-X Ctrl-E` keybinding to edit the current input buffer in an external editor.(v0.80.0)
  • Added repomap support for the Scala language.(v0.80.0)
  • Added support for the SOTA Gemini 2.5 Pro model.(v0.79.0)
  • Added support for the DeepSeek V3 0324 model.(v0.79.0)
  • Introduced a new /context command that automatically identifies which files need to be edited for a given request.(v0.79.0)
  • Added /edit as an alias for the /editor command.(v0.79.0)
  • Added an "overeager" mode for Claude 3.7 Sonnet models to help keep the model working within the requested scope.(v0.79.0)
  • Added support for thinking tokens when using OpenRouter Sonnet 3.7.(v0.78.0)
  • Introduced commands to switch between model types: /editor-model and /weak-model.(v0.78.0)
  • Added the --git-commit-verify flag to control whether git commit hooks are bypassed.(v0.78.0)
  • Added support for AWS_PROFILE when using Bedrock models, allowing use of AWS profiles for credentials.(v0.78.0)
  • Added support for the openrouter/google/gemma-3-27b-it model.(v0.78.0)
  • Enabled vi-like behavior when pressing enter in multiline-mode while in vi normal/navigation-mode.(v0.78.0)
  • Added /think-tokens command to set thinking token budget with support for human-readable formats (8k, 10.5k, 0.5M).(v0.77.0)
  • Added /reasoning-effort command to control model reasoning level.(v0.77.0)
  • Enabled support for Cohere model cohere_chat/command-a-03-2025 and Gemini model gemini/gemma-3-27b-it.(v0.77.0)
  • Added --auto-accept-architect flag to automatically accept changes from architect coder format without confirmation.(v0.77.0)
  • Added ability to control token budget for reasoning models using the new `--thinking-tokens` CLI option.(v0.76.0)
  • Enabled display of thinking/reasoning content returned by LLMs.(v0.76.0)
  • Introduced user notifications when the LLM has completed its last request and is waiting for input via the `--notifications` flag.(v0.76.0)
  • Added support for specifying a custom desktop notification command using `--notifications-command`.(v0.76.0)
  • Added support for the QWQ 32B model.(v0.76.0)
  • Added support for DeepSeek V3 free model on OpenRouter via `--model openrouter/deepseek/deepseek-chat:free`.(v0.76.0)
  • Added support for Claude 3.7 Sonnet models across OpenRouter, Bedrock, and Vertex AI.(v0.76.0)
  • Added support for the GPT-4.5-preview model.(v0.76.0)
  • Added support for Claude 3.7 Sonnet:beta on OpenRouter.(v0.76.0)
  • Added support for the `openrouter/anthropic/claude-3.7-sonnet` model.(v0.76.0)
  • Added an offer to install necessary dependencies when using Bedrock and Vertex AI models.(v0.76.0)
  • Added basic support for the Claude 3.7 Sonnet model (use --model sonnet).(v0.75.0)
  • Added support for the openrouter/o3-mini-high model configuration.(v0.75.0)
  • Added support for tree-sitter language packs.(v0.75.0)
  • Added HCL (Terraform) syntax support.(v0.75.0)
  • Enabled markdown generation for o1 & o3-mini models by sending a specific formatting string.(v0.75.0)
  • Enabled dynamic adjustment of the Ollama context window to match the current chat size.(v0.74.0)
  • Introduced the ability to specify a floating-point value for `use_temperature` in model settings, moving beyond simple true/false.(v0.74.0)
  • Added `boto3` to the full Docker container to enable support for Amazon Bedrock.(v0.74.0)
  • Enabled full support for the o3-mini model via the `aider --model o3-mini` command.(v0.73.0)
  • Introduced the new `--reasoning-effort` argument with options: low, medium, and high.(v0.73.0)
  • Added support for removing model-specific reasoning tags from responses using the `remove_reasoning: tagname` model setting.(v0.73.0)
  • Enabled automatic creation of parent directories when creating new files.(v0.73.0)
  • Added support for using the R1 free model on OpenRouter via `--model openrouter/deepseek/deepseek-r1:free`.(v0.73.0)
  • Added support for the DeepSeek R1 model, accessible via the `--model r1` shortcut or OpenRouter.(v0.72.0)
  • Introduced Kotlin syntax support to the repository map functionality.(v0.72.0)
  • Enabled the `--line-endings` option for controlling file writing line endings.(v0.72.0)
  • Added read-only file announcements to improve user awareness when files cannot be modified.(v0.72.0)

All MODELS Bug Fixes

  • Fixed an issue where new settings provided for an existing model failed to replace the old settings.(v0.86.0)
  • Fixed analytics to correctly support the latest PostHog SDK event-capture API.(v0.86.0)
  • Fixed Vertex AI model name prefixes in settings.(v0.85.0)
  • Fixed encoding issues in git diff output and LLM history logging.(v0.85.0)
  • Fixed search block regex to accept optional closing tags when working with HTML content.(v0.85.0)
  • Auto-created parent directories for chat history files to prevent startup errors.(v0.85.0)
  • Ensured pip is available before attempting package installation.(v0.85.0)
  • Fixed an issue where files explicitly added via the command line were not correctly ignored if listed in .gitignore.(v0.84.0)
  • Fixed OpenRouter token cost calculation for improved accuracy.(v0.84.0)
  • Fixed linter command execution on Windows by adopting `oslex` for argument quoting.(v0.83.0)
  • Fixed an issue where read-only status of files might not be preserved correctly by some commands (e.g. `/drop` after adding a read-only file).(v0.83.0)
  • Fixed an issue where the tool failed to automatically select the best edit format when using architect mode.(v0.82.0)
  • Fixed incorrect URL extraction from error messages.(v0.82.0)
  • Fixed quoting issues for values containing '#' within the sample `aider.conf.yml` file.(v0.82.0)
  • Fixed issue where Aider would retry API calls even when the provider indicated insufficient credits.(v0.81.0)
  • Fixed URL detection to correctly exclude trailing double quotes when parsing content.(v0.81.0)
  • Fixed linting errors for filepaths containing shell metacharacters.(v0.80.0)
  • Fixed a bug in the `/run` command that was preventing auto-testing.(v0.80.0)
  • Fixed a bug preventing `UnboundLocalError` during git tree traversal.(v0.80.0)
  • Handled `GitCommandNotFound` error if git is not installed or not in PATH.(v0.80.0)
  • Handled `FileNotFoundError` if the current working directory is deleted while aider is running.(v0.80.0)
  • Fixed autocompletion for /ask, /code, and /architect commands.(v0.78.0)
  • Fixed a bug where the default model was incorrectly set by deprecated --shortcut switches even when explicitly specified on the command line.(v0.77.0)
  • Fixed handling of JSONDecodeError when loading the model cache file.(v0.77.0)
  • Fixed handling of GitCommandError when retrieving git user configuration.(v0.77.0)
  • Fixed weak_model_name patterns to correctly match main model name patterns for certain models.(v0.76.0)
  • Fixed handling of Git errors encountered when reading staged files.(v0.76.0)
  • Fixed Git identity retrieval to properly respect global configuration settings.(v0.76.0)
  • Fixed an issue where the continuation prompt ". " was incorrectly included for multiline input.(v0.75.0)
  • Fixed a bug related to the /editor command.(v0.75.0)
  • Fixed an issue that caused the creation of incorrect filenames (e.g., `python`, `php`) during operations.(v0.74.0)
  • Resolved a bug related to the `--timeout` functionality.(v0.74.0)
  • Fixed an issue where the `/model` command incorrectly reported that the weak model had not been changed.(v0.74.0)
  • Ensured that multi-line mode now correctly persists across interruptions (^C) at confirmation prompts.(v0.74.0)
  • Fixed model metadata for the `openrouter/deepseek/deepseek-r1` model.(v0.73.0)
  • Fixed issues related to incorrect user/assistant turn order that caused errors when using R1 models.(v0.73.0)
  • Fixed an issue related to turn taking when reflecting linting or test errors.(v0.72.0)
  • Resolved a permissions issue present in Docker images.(v0.72.0)
  • Fixed an issue where ASCII fallback was incorrectly triggered during unicode errors.(v0.72.0)
  • Corrected integer indexing errors when calculating list slicing within repomap operations.(v0.72.0)

Releases with MODELS Changes

v0.86.05 features2 fixes
Aug 9, 2025

This release significantly expands model compatibility by adding support for all GPT-5 models, Grok-4, and several new preview and third-party models. Quality of life improvements include clearer feedback for the `/clear` command and cleaner output for `/undo`.

v0.85.010 features5 fixes
Jun 27, 2025

This release introduces significant model updates, including support for the new Gemini 2.5 series and Responses API models, alongside enhanced thinking token controls. Key new features focus on improving developer workflow, such as enabling gitignore file inclusion in scope and adding language specification for commit messages. Several fixes address encoding issues, model prefix errors, and startup stability.

v0.84.04 features2 fixes
May 30, 2025

This release significantly expands model support by adding the latest Claude 4 series models and Gemini 2.5 Flash preview. Key fixes include correcting file ignoring behavior and improving OpenRouter cost accuracy, alongside several quality-of-life enhancements like better commit message context and improved shell completion.

v0.83.012 features2 fixes
May 9, 2025

This release introduces significant model support, adding Gemini 2.5 Pro preview and Qwen models, alongside new commit attribution features like `--attribute-co-authored-by`. Enhancements include improved streaming spinners, better cross-platform command quoting via `oslex`, and automatic fetching of OpenRouter model parameters.

v0.82.07 features3 fixes
Apr 14, 2025

This release significantly expands model compatibility by adding support for GPT 4.1 variants and several new Grok and Optimus models. Key functional updates include the introduction of the `patch` edit format for GPT-4.1 and fixes for architect mode selection and URL extraction.

v0.81.02 features2 fixes
Apr 4, 2025

This release introduces support for the new Quasar Alpha model via OpenRouter and streamlines authentication by offering OAuth when API keys are missing. Several improvements focus on better error reporting for OpenRouter connections and fixing issues related to retrying failed API calls.

v0.80.06 features5 fixes
Mar 31, 2025

This release introduces significant integration updates, including OpenRouter OAuth support and new model availability. Several critical bugs related to filepaths, git operations, and the /run command have been resolved. Additionally, the tool now provides better startup validation for configurations and improves handling of external dependencies like git.

v0.79.05 features
Mar 25, 2025

This release focuses heavily on expanding model compatibility by adding support for Gemini 2.5 Pro and DeepSeek V3 0324. New context management features, including the /context command, improve workflow efficiency by automatically identifying necessary files for edits.

v0.78.06 features1 fix
Mar 21, 2025

This release introduces new model configuration flexibility, including support for thinking tokens with OpenRouter Sonnet 3.7 and AWS_PROFILE support for Bedrock models. Key usability enhancements include new commands for switching model types and fixes for autocompletion across several core commands.

v0.77.04 features3 fixes
Mar 13, 2025

This release introduces powerful new configuration commands, /think-tokens and /reasoning-effort, allowing fine-grained control over model behavior and budget. It also brings massive expansion to supported programming languages via tree-sitter integration and fixes several critical bugs related to model configuration and file handling.

v0.76.011 features3 fixes
Mar 10, 2025

This release significantly enhances reasoning model support by adding token budget control and displaying reasoning output directly. Aider now offers user notifications when LLM responses are ready and introduces broad support for new models like QWQ 32B and Claude 3.7 Sonnet across various providers. Additionally, several Git and configuration handling bugs have been resolved.

v0.75.05 features2 fixes
Mar 4, 2025

This release introduces basic support for the Claude 3.7 Sonnet model and expands language support with HCL (Terraform) and tree-sitter pack integration. Several bugs were fixed, particularly concerning multiline input continuation prompts and the /editor command.

v0.74.03 features4 fixes
Feb 6, 2025

This release focuses on enhancing model integration and stability, including dynamic context window management for Ollama and improved support for various secondary API providers. Key fixes address incorrect filename generation and ensure multi-line mode persists through interruptions. Users will also benefit from faster startup times and better Docker environment configuration.

v0.73.05 features2 fixes
Jan 31, 2025

This release introduces significant model flexibility with full support for o3-mini and R1 free on OpenRouter, alongside a new `--reasoning-effort` control. Key improvements include better context window handling and fixes to ensure correct turn ordering for R1 models.

v0.72.04 features4 fixes
Jan 20, 2025

This release introduces support for the new DeepSeek R1 model and adds Kotlin syntax support to the repository map feature. Several bugs were fixed, including issues with turn taking during error reflection and incorrect list slicing in repomap calculations. Users also gain control over file line endings via a new command-line option.

Documentation

Read the models documentation