cleanup --model-metadata-file

website/docs/aider_conf.md

@@ -89,6 +89,9 @@ cog.outl("```")
 ## Specify the OpenAI organization ID
 #openai-organization-id:
 
+## Specify a file with context window and costs for unknown models
+#model-metadata-file:
+
 ## Specify what edit format the LLM should use (default depends on model)
 #edit-format:
 

website/docs/install/optional.md

@@ -26,27 +26,6 @@ Put a line in it like this to specify your api key:
 openai-api-key: sk-...
 ```
 
-## Registering Models not in litellm 
-
-You can register model info and costs with litellm by adding one or more of the following files
-* {HomeDir}/.aider.models.json
-* {GitRoot}/.aider.models.json
-* {CWD}/.aider.models.json
-* or via the command line argument `model-file`
-If the files above exists, they will be loaded in that order. Files loaded last will take priority.
-The json file should be formated as follows
-```
-{
-  "gpt-4": {
-    "max_tokens": 8192,
-    "input_cost_per_token": 0.00003,
-    "output_cost_per_token": 0.00006,
-    "litellm_provider": "openai",
-    "mode": "chat",
-  },
-}
-```
-see [litellm's model definitions](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json) for examples
 
 ## Enable Playwright 
 

website/docs/llms/warnings.md

@@ -6,3 +6,38 @@ nav_order: 900
 # Model warnings
 
 {% include model-warnings.md %}
+
+
+## Specifying context window size and token costs
+
+You can register context window limits and costs for models that aren't known
+to aider. Create a `.aider.models.json` file in one of these locations:
+
+- Your home directory.
+- The root if your git repo.
+- The current directory where you launch aider.
+- Or specify a specific file with the `--model-metadata-file <filename>` switch.
+
+
+If the files above exist, they will be loaded in that order. 
+Files loaded last will take priority.
+
+The json file should be a dictionary with an entry for each model, as follows:
+
+```
+{
+    "gpt-4": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 8192,
+        "max_output_tokens": 4096, 
+        "input_cost_per_token": 0.00003,
+        "output_cost_per_token": 0.00006,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_function_calling": true
+    }
+}
+```
+
+See 
+[litellm's model_prices_and_context_window.json file](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json) for more examples.

website/docs/options.md

@@ -19,7 +19,7 @@ usage: aider [-h] [--vim] [--openai-api-key] [--anthropic-api-key]
              [--35turbo] [--models] [--openai-api-base]
              [--openai-api-type] [--openai-api-version]
              [--openai-api-deployment-id] [--openai-organization-id]
-             [--edit-format] [--weak-model]
+             [--model-metadata-file] [--edit-format] [--weak-model]
              [--show-model-warnings | --no-show-model-warnings]
              [--map-tokens] [--max-chat-history-tokens] [--env-file]
              [--input-history-file] [--chat-history-file]
@@ -108,10 +108,6 @@ Aliases:
 List known models which match the (partial) MODEL name  
 Environment variable: `AIDER_MODELS`  
 
-### `--model-file FILE`
-Specify a file with model definitions (info and cost) to be registered with litellm, json formated. See [Registering Models not in litellm](install/optional.md#registering_models_not_in_litellm) for the format  
-Environment variable: `AIDER_MODEL_FILE`
-
 ### `--openai-api-base OPENAI_API_BASE`
 Specify the api base url  
 Environment variable: `OPENAI_API_BASE`  
@@ -132,6 +128,10 @@ Environment variable: `OPENAI_API_DEPLOYMENT_ID`
 Specify the OpenAI organization ID  
 Environment variable: `OPENAI_ORGANIZATION_ID`  
 
+### `--model-metadata-file MODEL_FILE`
+Specify a file with context window and costs for unknown models  
+Environment variable: `AIDER_MODEL_METADATA_FILE`  
+
 ### `--edit-format EDIT_FORMAT`
 Specify what edit format the LLM should use (default depends on model)  
 Environment variable: `AIDER_EDIT_FORMAT`