docs: remove specific model IDs and version numbers from provider documentation

- Remove hardcoded model names/IDs that quickly become outdated
- Replace with generic references to model families and catalogs
- Keep examples only where necessary for technical understanding (file formats, syntax)

Updated files:
- vscode-lm.md: Remove specific model examples
- openai.md: Clean keywords and remove version-specific references
- bedrock.md: Remove dated model ID examples
- litellm.md: Use generic placeholders in config examples
- vercel-ai-gateway.md: Remove default model reference
- qwen-code.md: Replace specific model list with catalog reference
- gemini.md: Remove version-specific model mention
- zai.md: Change from 'GLM-4.5' to 'GLM family'

Author: Sannidhya

docs/providers/bedrock.md

@@ -53,7 +53,7 @@ Roo Code supports all foundation models available through Amazon Bedrock.
 
 For the complete, up-to-date model list with IDs and capabilities, see [AWS Bedrock's supported models documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html).
 
-**Important:** Use the *model ID* (e.g., `anthropic.claude-sonnet-4-5-20250929-v1:0`) when configuring Roo Code, not the model name.
+**Important:** Use the *model ID* when configuring Roo Code, not the model name.
 
 ---
 
@@ -84,7 +84,7 @@ Roo Code supports using the reasoning budget (extended thinking) for Anthropic's
 
 To enable the reasoning budget:
 
-1.  **Select a supported Claude model** (e.g., `anthropic.claude-opus-4.1-20250514-v1:0`, `anthropic.claude-3-sonnet-20240229-v1:0`).
+1.  **Select a supported Claude model** that includes reasoning capabilities.
 2.  **Enable Reasoning Mode** in the model settings.
 3.  **Adjust the thinking budget** to control how much the model should "think".
 

docs/providers/gemini.md

@@ -46,7 +46,7 @@ For the complete, up-to-date model list and capabilities, see [Google's Gemini m
 3.  **Enter API Key:** Paste your Gemini API key into the "Gemini API Key" field.
 4.  **Select Model:** Choose your desired Gemini model from the "Model" dropdown.
 
-By default, Roo Code selects a stable Pro model (currently a Gemini 2.5 Pro variant) with a temperature of **1.0** where your provider supports it. This keeps suggestions more expressive and natural while still staying on task. If you need highly deterministic output (for example, for code generation in CI), you can lower the temperature toward `0.0`.
+By default, Roo Code selects a stable Pro model with a temperature of **1.0** where your provider supports it. This keeps suggestions more expressive and natural while still staying on task. If you need highly deterministic output (for example, for code generation in CI), you can lower the temperature toward `0.0`.
 
 ---
 

docs/providers/litellm.md

@@ -48,19 +48,19 @@ To use LiteLLM with Roo Code, you first need to set up and run a LiteLLM server.
    ```yaml
    model_list:
      # Configure Anthropic models
-     - model_name: claude-3-7-sonnet
+     - model_name: claude-sonnet
        litellm_params:
-         model: anthropic/claude-3-7-sonnet-20250219
+         model: anthropic/claude-sonnet-model-id
          api_key: os.environ/ANTHROPIC_API_KEY
 
      # Configure OpenAI models
-     - model_name: gpt-4o
+     - model_name: gpt-model
        litellm_params:
-         model: openai/gpt-4o
+         model: openai/gpt-model-id
          api_key: os.environ/OPENAI_API_KEY
 
      # Configure Azure OpenAI
-     - model_name: azure-gpt-4
+     - model_name: azure-model
        litellm_params:
          model: azure/my-deployment-name
          api_base: https://your-resource.openai.azure.com/
@@ -77,7 +77,7 @@ To use LiteLLM with Roo Code, you first need to set up and run a LiteLLM server.
 
    # Or quick start with a single model
    export ANTHROPIC_API_KEY=your-anthropic-key
-   litellm --model claude-3-7-sonnet-20250219
+   litellm --model anthropic/claude-model-id
    ```
 
 4. The proxy will run at `http://0.0.0.0:4000` by default (accessible as `http://localhost:4000`).
@@ -105,7 +105,7 @@ Once your LiteLLM server is running, you have two options for configuring it in
     *   Roo Code will attempt to fetch the list of available models from your LiteLLM server by querying the `${baseUrl}/v1/model/info` endpoint.
     *   The models displayed in the dropdown are sourced from this endpoint.
     *   Use the refresh button to update the model list if you've added new models to your LiteLLM server.
-    *   If no model is selected, Roo Code defaults to `anthropic/claude-3-7-sonnet-20250219` (this is `litellmDefaultModelId`). Ensure this model (or your desired default) is configured and available on your LiteLLM server.
+    *   If no model is selected, Roo Code will use a default model. Ensure you have configured at least one model on your LiteLLM server.
 
 ### Option 2: Using OpenAI Compatible Provider
 
@@ -133,7 +133,7 @@ When you configure the LiteLLM provider, Roo Code interacts with your LiteLLM se
     *   `supportsImages`: Determined from `model_info.supports_vision` provided by LiteLLM.
     *   `supportsPromptCache`: Determined from `model_info.supports_prompt_caching` provided by LiteLLM.
     *   `inputPrice` / `outputPrice`: Calculated from `model_info.input_cost_per_token` and `model_info.output_cost_per_token` from LiteLLM.
-    *   `supportsComputerUse`: This flag is set to `true` if the underlying model identifier (from `litellm_params.model`, e.g., `openrouter/anthropic/claude-3.5-sonnet`) matches one of the Anthropic models predefined in Roo Code as suitable for "computer use" (see `COMPUTER_USE_MODELS` in technical details).
+    *   `supportsComputerUse`: This flag is set to `true` if the underlying model identifier matches one of the Anthropic models predefined in Roo Code as suitable for "computer use" (see `COMPUTER_USE_MODELS` in technical details).
 
 Roo Code uses default values for some of these properties if they are not explicitly provided by your LiteLLM server's `/model/info` endpoint for a given model. The defaults are:
 *   `maxTokens`: 8192

docs/providers/openai.md

@@ -1,15 +1,12 @@
 ---
 sidebar_label: OpenAI
-description: Connect Roo Code to OpenAI's official API for access to GPT-5, GPT-4o, o1, and o3 models with advanced reasoning capabilities and verbosity control.
+description: Connect Roo Code to OpenAI's official API for access to GPT and reasoning models with advanced capabilities and verbosity control.
 keywords:
   - OpenAI
-  - GPT-5
-  - GPT-4o
-  - o1 models
-  - o3-mini
+  - GPT models
+  - reasoning models
   - Roo Code
   - AI integration
-  - reasoning models
   - API key
   - official OpenAI API
   - verbosity
@@ -49,7 +46,7 @@ For the complete, up-to-date model list and capabilities, see [OpenAI's models d
 1.  **Open Roo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel.
 2.  **Select Provider:** Choose "OpenAI" from the "API Provider" dropdown.
 3.  **Enter API Key:** Paste your OpenAI API key into the "OpenAI API Key" field.
-4.  **Select Model:** Choose your desired model from the "Model" dropdown (defaults to `gpt-5.1`).
+4.  **Select Model:** Choose your desired model from the "Model" dropdown.
 5.  **(Optional) Base URL:** If you need to use a custom base URL, enter the URL. Most people won't need to adjust this.
 
 ---
@@ -71,7 +68,7 @@ For models that support reasoning (GPT-5, o1, o3, o4 families), you can control
 - `medium` - Balanced approach
 - `high` - Maximum thinking for complex problems
 
-Some models have preset reasoning levels (e.g., `o3-high` always uses high reasoning).
+Some models have preset reasoning levels that cannot be changed.
 
 ### Verbosity Control
 

docs/providers/qwen-code.md

@@ -31,11 +31,9 @@ Access Alibaba's Qwen3 Coder models through OAuth authentication with automatic
 
 ## Available Models
 
-Both Qwen3 Coder models feature massive 1M context windows and 65K max output tokens.
+Qwen3 Coder models feature massive 1M context windows and 65K max output tokens.
 
-**Available models:**
-- **qwen3-coder-plus** - High-performance coding model (default)
-- **qwen3-coder-flash** - Speed-optimized variant
+For the complete, up-to-date model list, see the Qwen Code provider's model catalog when you configure the provider in Roo Code.
 
 ---
 

docs/providers/vercel-ai-gateway.md

@@ -41,8 +41,6 @@ Roo Code automatically fetches all available models from Vercel AI Gateway's API
 
 For the complete, up-to-date model catalog with capabilities, see [Vercel's AI Gateway models page](https://vercel.com/ai-gateway/models).
 
-**Default:** `anthropic/claude-sonnet-4` if no model is selected.
-
 ---
 
 ## Configuration in Roo Code

docs/providers/vscode-lm.md

@@ -36,11 +36,7 @@ Roo Code includes *experimental* support for the [VS Code Language Model API](ht
 
 1.  **Open Roo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel.
 2.  **Select Provider:** Choose "VS Code LM API" from the "API Provider" dropdown.
-3.  **Select Model:**  The "Language Model" dropdown will (eventually) list available models. The format is `vendor/family`. For example, if you have Copilot, you might see options like:
-    *   `copilot - claude-3.5-sonnet`
-    *   `copilot - o3-mini`
-    *   `copilot - o1-ga`
-    *   `copilot - gemini-2.0-flash`
+3.  **Select Model:**  The "Language Model" dropdown will (eventually) list available models. The format is `vendor/family`. For example, if you have Copilot, you might see options like `copilot - <model-name>`.
 
 ---
 

docs/providers/zai.md

@@ -1,11 +1,11 @@
 ---
 sidebar_label: Z AI
-description: Configure Z AI models in Roo Code. Access GLM-4.5 series models with region-aware routing for international and China mainland users.
+description: Configure Z AI models in Roo Code. Access GLM family models with region-aware routing for international and China mainland users.
 keywords:
   - z ai
   - zai
   - zhipu ai
-  - glm-4.5
+  - glm models
   - roo code
   - api provider
   - china ai
@@ -16,7 +16,7 @@ image: /img/social-share.jpg
 
 # Using Z AI With Roo Code
 
-Z AI (Zhipu AI) provides advanced language models with the GLM-4.5 series. The provider offers region-aware routing with separate endpoints for international users and China mainland users.
+Z AI (Zhipu AI) provides advanced language models with the GLM family. The provider offers region-aware routing with separate endpoints for international users and China mainland users.
 
 **Website:** [https://z.ai/model-api](https://z.ai/model-api) (International) | [https://open.bigmodel.cn/](https://open.bigmodel.cn/) (China)