diff --git a/aider/website/docs/config/model-aliases.md b/aider/website/docs/config/model-aliases.md index ae32c80b1..471005c39 100644 --- a/aider/website/docs/config/model-aliases.md +++ b/aider/website/docs/config/model-aliases.md @@ -13,7 +13,7 @@ Model aliases allow you to create shorthand names for models you frequently use. You can define aliases when launching aider using the `--alias` option: ```bash -aider --alias "fast:gpt-3.5-turbo" --alias "smart:gpt-4" +aider --alias "fast:gpt-4o-mini" --alias "smart:o3-mini" ``` Multiple aliases can be defined by using the `--alias` option multiple times. Each alias definition should be in the format `alias:model-name`. @@ -24,8 +24,8 @@ You can also define aliases in your [`.aider.conf.yml` file](https://aider.chat/ ```yaml alias: - - "fast:gpt-3.5-turbo" - - "smart:gpt-4" + - "fast:gpt-4o-mini" + - "smart:o3-mini" - "hacker:claude-3-sonnet-20240229" ``` @@ -34,8 +34,8 @@ alias: Once defined, you can use the alias instead of the full model name: ```bash -aider --model fast # Uses gpt-3.5-turbo -aider --model smart # Uses gpt-4 +aider --model fast # Uses gpt-4o-mini +aider --model smart # Uses o3-mini ``` ## Built-in Aliases diff --git a/aider/website/docs/llms/openai.md b/aider/website/docs/llms/openai.md index 4be98041d..f39d3927f 100644 --- a/aider/website/docs/llms/openai.md +++ b/aider/website/docs/llms/openai.md @@ -8,7 +8,7 @@ nav_order: 100 To work with OpenAI's models, you need to provide your [OpenAI API key](https://help.openai.com/en/articles/4936850-where-do-i-find-my-secret-api-key) either in the `OPENAI_API_KEY` environment variable or -via the `--openai-api-key` command line switch. +via the `--api-key openai=` command line switch. Aider has some built in shortcuts for the most popular OpenAI models and has been tested and benchmarked to work well with them: @@ -16,28 +16,34 @@ has been tested and benchmarked to work well with them: ``` python -m pip install -U aider-chat -export OPENAI_API_KEY= # Mac/Linux -setx OPENAI_API_KEY # Windows, restart shell after setx - -# Aider uses gpt-4o by default (or use --4o) -aider - -# GPT-4o -aider --4o - -# GPT-3.5 Turbo -aider --35-turbo +# o3-mini +aider --model o3-mini --api-key openai= # o1-mini -aider --model o1-mini +aider --model o1-mini --api-key openai= -# o1-preview -aider --model o1-preview +# GPT-4o +aider --4o --api-key openai= # List models available from OpenAI aider --list-models openai/ + +# You can also store you API key in environment variables (or .env) +export OPENAI_API_KEY= # Mac/Linux +setx OPENAI_API_KEY # Windows, restart shell after setx ``` You can use `aider --model ` to use any other OpenAI model. For example, if you want to use a specific version of GPT-4 Turbo you could do `aider --model gpt-4-0125-preview`. + +## o1 models from other providers + +Many of OpenAI's o1 +"reasoning" models have restrictions on streaming and setting the temperature parameter. +Aider is configured to work properly with these models +when served through major provider APIs. + +You may need to [configure reasoning model settings](/docs/config/reasoning.html) +if you are using them through another provider +and see errors related to temperature or system prompt. diff --git a/aider/website/docs/troubleshooting/models-and-keys.md b/aider/website/docs/troubleshooting/models-and-keys.md index c74dcff6c..1ee24733c 100644 --- a/aider/website/docs/troubleshooting/models-and-keys.md +++ b/aider/website/docs/troubleshooting/models-and-keys.md @@ -16,13 +16,13 @@ aider --model deepseek --api-key deepseek=your-key-goes-here # Work with Claude 3.5 Sonnet via Anthropic's API aider --model sonnet --api-key anthropic=your-key-goes-here -# Work with GPT-4o via OpenAI's API -aider --model gpt-4o --api-key openai=your-key-goes-here +# Work with o3-mini via OpenAI's API +aider --model o3-mini --api-key openai=your-key-goes-here # Work with Sonnet via OpenRouter's API aider --model openrouter/anthropic/claude-3.5-sonnet --api-key openrouter=your-key-goes-here -# Work with DeepSeek via OpenRouter's API +# Work with DeepSeek Chat V3 via OpenRouter's API aider --model openrouter/deepseek/deepseek-chat --api-key openrouter=your-key-goes-here ``` diff --git a/aider/website/docs/troubleshooting/token-limits.md b/aider/website/docs/troubleshooting/token-limits.md index 9cbf79b78..31e12e224 100644 --- a/aider/website/docs/troubleshooting/token-limits.md +++ b/aider/website/docs/troubleshooting/token-limits.md @@ -29,7 +29,7 @@ Total tokens: 4864 of 16385 To reduce output tokens: - Ask for smaller changes in each request. - Break your code into smaller source files. -- Try using a stronger model like gpt-4o or opus that can return diffs. +- Try using a stronger model like DeepSeek V3 or Sonnet that can return diffs. For more info: https://aider.chat/docs/token-limits.html ``` @@ -47,7 +47,7 @@ overflowing its context window. Technically you can exhaust the context window if the input is too large or if the input plus output are too large. -Strong models like GPT-4o and Opus have quite +Strong models like GPT-4o and Sonnet have quite large context windows, so this sort of error is typically only an issue when working with weaker models. @@ -73,7 +73,7 @@ To avoid hitting output token limits: - Ask for smaller changes in each request. - Break your code into smaller source files. -- Use a strong model like gpt-4o, sonnet or opus that can return diffs. +- Use a strong model like gpt-4o, sonnet or DeepSeek V3 that can return diffs. - Use a model that supports [infinite output](/docs/more/infinite-output.html). ## Other causes diff --git a/aider/website/docs/usage.md b/aider/website/docs/usage.md index 2c15cadf6..76f0ac980 100644 --- a/aider/website/docs/usage.md +++ b/aider/website/docs/usage.md @@ -68,11 +68,11 @@ relevant context from the rest of your repo. {% include works-best.md %} ``` -# GPT-4o -$ aider --4o +# o3-mini +$ aider --model o3-mini --api-key openai= # Claude 3.5 Sonnet -$ aider --sonnet +$ aider --model sonnet --api-key anthropic= ``` Or you can run `aider --model XXX` to launch aider with