Address PR #432 review: fix broken URL and remove unnecessary promotional content from provider docs

Sannidhya · Sannidhya · commit c79f32fb5cd5 · 2025-12-03T00:09:45.000+05:30
diff --git a/docs/providers/anthropic.md b/docs/providers/anthropic.md
@@ -38,11 +38,6 @@ Roo Code supports all Claude models available through Anthropic's API.
 
 For the complete, up-to-date model list and capabilities, see [Anthropic's model documentation](https://docs.anthropic.com/en/docs/about-claude/models).
 
-**Recommended for Roo Code:**
-- **Sonnet models** - Best balance of performance and cost for most coding tasks (default)
-- **Opus models** - Better for complex reasoning and large-scale refactoring
-- **Haiku models** - Faster and more cost-effective for simpler tasks
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/bedrock.md b/docs/providers/bedrock.md
@@ -55,13 +55,6 @@ For the complete, up-to-date model list with IDs and capabilities, see [AWS Bedr
 
 **Important:** Use the *model ID* (e.g., `anthropic.claude-sonnet-4-5-20250929-v1:0`) when configuring Roo Code, not the model name.
 
-**Recommended for Roo Code:**
-- **Claude Sonnet models** - Best balance for most coding tasks (default: `anthropic.claude-sonnet-4-5-20250929-v1:0`)
-- **Amazon Nova models** - Better for AWS-integrated workflows
-- **Meta Llama models** - Good for open-source requirements
-
-**Note:** Model availability varies by AWS region. Request access to specific models through the Bedrock console before use.
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/cerebras.md b/docs/providers/cerebras.md
@@ -45,12 +45,7 @@ Cerebras AI specializes in extremely fast inference speeds (up to 2600 tokens/se
 
 Roo Code automatically fetches all available models from Cerebras AI's API.
 
-For the complete, up-to-date model list and pricing, see [Cerebras Cloud](https://cloud.cerebras. ai?utm_source=roocode).
-
-**Key advantages:**
-- Ultra-fast inference (up to 2600 tokens/second)
-- Free tier available with rate limits
-- Context windows: 64K-128K tokens
+For the complete, up-to-date model list and pricing, see [Cerebras Cloud](https://cloud.cerebras.ai?utm_source=roocode).
 
 ---
 
diff --git a/docs/providers/chutes.md b/docs/providers/chutes.md
@@ -33,8 +33,6 @@ Roo Code automatically fetches all available models from Chutes AI's API.
 
 For the complete, up-to-date model list, see [Chutes AI's platform](https://chutes.ai/) or your account dashboard.
 
-**Key advantage:** Free API access to multiple LLMs for experimentation and development.
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/claude-code.md b/docs/providers/claude-code.md
@@ -42,21 +42,6 @@ If this environment variable is set on your system, the `claude` tool may use it
 
 ---
 
-## Key Features
-- **Direct CLI Access**: Uses Anthropic's official Claude CLI tool for model interactions.
-- **Advanced Reasoning**: Full support for Claude's thinking mode and reasoning capabilities.
-- **Cost Transparency**: Shows exact usage costs as reported by the CLI.
-- **Flexible Configuration**: Works with your existing Claude CLI setup.
-
----
-
-## Why Use This Provider
-
-- **No API Keys**: Uses your existing Claude CLI authentication.
-- **Cost Benefits**: Leverage CLI subscription rates and transparent cost reporting.
-- **Latest Features**: Access new Claude capabilities as they're released in the CLI.
-- **Advanced Reasoning**: Full support for Claude's thinking modes.
-
 ## How it Works
 
 The Claude Code provider works by:
@@ -100,12 +85,6 @@ The Claude Code provider supports all Claude models available through the offici
 
 Model availability depends on your Claude CLI subscription and plan. See [Anthropic's CLI documentation](https://docs.anthropic.com/en/docs/claude-code/setup) for details.
 
-**Recommended:**
-- **Sonnet models** - Best balance for most coding tasks (latest recommended)
-- **Opus models** - Better for complex reasoning
-- **Haiku models** - Faster responses when speed matters
-
-
 ---
 
 ## Output Token Limits
diff --git a/docs/providers/deepinfra.md b/docs/providers/deepinfra.md
@@ -37,52 +37,11 @@ Roo Code automatically fetches all available models from DeepInfra's API.
 
 For the complete, up-to-date model catalog, see [DeepInfra's models page](https://deepinfra.com/models).
 
-**Recommended for Roo Code:**
-- **Qwen Coder models** - Best for programming tasks with large context windows (default: `Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo`)
-- **Vision-capable models** - Better when you need image understanding
-- **Reasoning models** - Best for complex problem-solving tasks
-
-**Key features:** Prompt caching support, low latency with global edge locations, competitive pricing.
-
 ---
 
 ## Configuration in Roo Code
 
 1. **Open Roo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel.
 2. **Select Provider:** Choose "DeepInfra" from the "API Provider" dropdown.
 3. **Enter API Key:** Paste your DeepInfra API key into the "DeepInfra API Key" field.
-4. **Select Model:** Choose your desired model from the "Model" dropdown.
-   - Models will auto-populate after entering a valid API key
-   - Click "Refresh Models" to update the list
-
----
-
-## Advanced Features
-
-### Prompt Caching
-
-DeepInfra supports prompt caching for eligible models, which:
-- Reduces costs for repeated contexts
-- Improves response times for similar queries
-- Automatically manages cache based on task IDs
-
-### Vision Support
-
-Models with vision capabilities can:
-- Process images alongside text
-- Understand visual content for coding tasks
-- Analyze screenshots and diagrams
-
-### Custom Base URL
-
-For enterprise deployments, you can configure a custom base URL in the advanced settings.
-
----
-
-## Tips and Notes
-
-* **Performance:** DeepInfra offers low latency with automatic load balancing across global locations.
-* **Cost Efficiency:** Competitive pricing with prompt caching to reduce costs for repeated contexts.
-* **Model Variety:** Access to the latest open-source models including specialized coding models.
-* **Context Windows:** Models support context windows up to 256K tokens for large codebases.
-* **Pricing:** Pay-per-use model with no minimums. Check [deepinfra.com](https://deepinfra.com/) for current pricing.
+4. **Select Model:** Choose your desired model from the "Model" dropdown.
diff --git a/docs/providers/deepseek.md b/docs/providers/deepseek.md
@@ -36,10 +36,6 @@ Roo Code supports all models available through the DeepSeek API.
 
 For the complete, up-to-date model list, see [DeepSeek's API documentation](https://api-docs.deepseek.com/quick_start/pricing).
 
-**Recommended for Roo Code:**
-- **`deepseek-chat`** - Best for general coding tasks
-- **`deepseek-reasoner`** - Better for complex reasoning and problem-solving
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/doubao.md b/docs/providers/doubao.md
@@ -36,16 +36,6 @@ Roo Code supports all Doubao models available through ByteDance's Volcano Engine
 
 For the complete, up-to-date model list, see [Volcano Engine's AI model service](https://www.volcengine.com/).
 
-**Model features:**
-- 128K context window
-- Image input support
-- Prompt caching with 80% discount on cached reads
-
-**Recommended:**
-- General purpose: Standard models for everyday tasks
-- Thinking models: Better for enhanced reasoning
-- Flash models: Faster for speed-optimized workflows
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/featherless.md b/docs/providers/featherless.md
@@ -38,34 +38,11 @@ Roo Code automatically fetches all available models from Featherless AI's API.
 
 For the complete, up-to-date model list, see [Featherless AI](https://featherless.ai).
 
-**All models are currently FREE** with no usage costs.
-
-**Recommended for Roo Code:**
-- **DeepSeek R1 models** - Best for complex reasoning with `<think>` tag support (default)
-- **Qwen3 Coder** - Better for specialized code generation tasks
-- **Kimi K2** - Good for balanced instruction-following
-
-**Note:** Most models have ~32K context window and 4K max output. No image support or prompt caching available.
-
 ---
 
 ## Configuration in Roo Code
 
 1. **Open Roo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel.
 2. **Select Provider:** Choose "Featherless AI" from the "API Provider" dropdown.
 3. **Enter API Key:** Paste your Featherless API key into the "Featherless API Key" field.
-4. **Select Model:** Choose your desired model from the "Model" dropdown.
-
----
-
-## Tips and Notes
-
-* **Free Tier:** All models are currently free with no usage costs, making Featherless ideal for experimentation and development.
-* **Model Selection:** Choose models based on your needs:
-  - **DeepSeek R1 models:** Best for complex reasoning and problem-solving tasks
-  - **DeepSeek V3:** General-purpose model for various tasks
-  - **Qwen3 Coder:** Optimized for code generation and programming tasks
-  - **Kimi K2:** Balanced instruction-following model
-  - **GPT-OSS:** Large general-purpose model
-* **OpenAI Compatibility:** Featherless uses an OpenAI-compatible API format for easy integration.
-* **Limitations:** No image support or prompt caching available on any model.
+4. **Select Model:** Choose your desired model from the "Model" dropdown.
diff --git a/docs/providers/fireworks.md b/docs/providers/fireworks.md
@@ -44,44 +44,17 @@ Roo Code supports all models available through Fireworks AI's platform.
 
 For the complete, up-to-date model list and specifications, see [Fireworks AI's models page](https://fireworks.ai/models).
 
-**Recommended for Roo Code:**
-- **Kimi K2** - Best for general-purpose coding with agentic capabilities (default)
-- **Qwen3 Coder** - Better for specialized code generation and debugging
-- **DeepSeek R1** - Best for complex reasoning and function calling tasks
-- **Qwen3 235B** - Most cost-effective for general development work
-
 ---
 
 ## Configuration in Roo Code
 
 1. **Open Roo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel.
 2. **Select Provider:** Choose "Fireworks AI" from the "API Provider" dropdown.
 3. **Enter API Key:** Paste your Fireworks AI API key into the "Fireworks AI API Key" field.
-4. **Model Selection:** The default model (Kimi K2) is automatically selected. You can change it from the model dropdown if needed.
-
----
-
-## Model Selection Guide
-
-Choose models based on your needs:
-
-| Model | Best For | Context | Price |
-|-------|----------|---------|-------|
-| **Kimi K2** | General tasks, balanced performance | 128K | Mid-range |
-| **Qwen3 235B** | Cost-effective general use | 256K | Budget-friendly |
-| **Qwen3 Coder** | Code generation and debugging | 256K | Mid-range |
-| **DeepSeek R1** | Complex reasoning, function calling | 160K | Premium |
-| **DeepSeek V3** | Strong general performance | 128K | Balanced |
+4. **Select Model:** Choose your desired model from the "Model" dropdown.
 
 ---
 
 ## Tips and Notes
 
-* **Cost-Effective:** Fireworks AI offers significantly lower pricing than proprietary models while maintaining competitive performance.
-* **Large Context Windows:** Most models support 128K-256K tokens, suitable for processing large documents and maintaining extended conversations.
-* **OpenAI Compatibility:** The provider uses an OpenAI-compatible API format with streaming support and usage tracking.
-* **Rate Limits:** Fireworks AI has usage-based rate limits. Monitor your usage in the dashboard and consider upgrading your plan if needed.
-* **Text-Only:** All models are text-only without image support or prompt caching capabilities.
-* **Default Temperature:** Uses 0.5 temperature by default for balanced creativity and consistency.
-* **API Keys:** Stored locally on your machine for security.
-* **Pricing:** See the [Fireworks AI pricing page](https://fireworks.ai/pricing) for current rates. Prices shown are per million tokens.
+* **Pricing:** See the [Fireworks AI pricing page](https://fireworks.ai/pricing) for current rates.
diff --git a/docs/providers/gemini.md b/docs/providers/gemini.md
@@ -37,14 +37,6 @@ Roo Code supports all Gemini models available through Google's API and automatic
 
 For the complete, up-to-date model list and capabilities, see [Google's Gemini models documentation](https://ai.google.dev/models/gemini).
 
-**Recommended for Roo Code:**
-- **Gemini Pro models** - Best for complex coding, debugging, and analysis (Roo Code defaults to stable Pro variant)
-- **Gemini Flash models** - Faster and more cost-effective for everyday tasks
-- **Gemini 3 Pro Preview** - Better for very large workspaces with 1M-token context window
-- **Reasoning-capable models** - Best for multi-step planning (requires enabling reasoning budget in settings)
-
-**Pro tip:** Use model aliases (`gemini-flash-latest`, `gemini-pro-latest`) instead of version-specific IDs to automatically track Google's latest stable releases.
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/glama.md b/docs/providers/glama.md
@@ -36,12 +36,6 @@ Roo Code automatically fetches all available models from Glama's unified API.
 
 For the complete, up-to-date model list, see [Glama's models page](https://glama.ai/models).
 
-**Recommended for Roo Code:**
-- **Claude models** - Best performance for most tasks (e.g., `anthropic/claude-3-5-sonnet`)
-- **OpenAI models** - Good for specific reasoning tasks (e.g., `openai/o3-mini-high`)
-
-**Key features:** Prompt caching support, unified billing across providers, cost tracking.
-
 ---
 
 ## Configuration in Roo Code
@@ -56,4 +50,3 @@ For the complete, up-to-date model list, see [Glama's models page](https://glama
 ## Tips and Notes
 
 * **Pricing:** Glama operates on a pay-per-use basis.  Pricing varies depending on the model you choose.
-* **Prompt Caching:** Glama supports prompt caching, which can significantly reduce costs and improve performance for repeated prompts.
diff --git a/docs/providers/groq.md b/docs/providers/groq.md
@@ -34,8 +34,6 @@ Roo Code automatically fetches all available models from the Groq API.
 
 For the complete, up-to-date model list and capabilities, see [Groq's models documentation](https://console.groq.com/docs/models).
 
-**Key advantage:** Groq's custom LPUs deliver significantly faster inference speeds compared to traditional GPUs, resulting in quicker response times for all supported models.
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/huggingface.md b/docs/providers/huggingface.md
@@ -36,13 +36,9 @@ Roo Code integrates with the Hugging Face router to provide access to a curated
 
 ## Available Models
 
-Roo Code automatically fetches models from the curated 'roocode' collection on Hugging Face, optimized for code assistance.
+Roo Code automatically fetches all available models from the curated 'roocode' collection on Hugging Face.
 
-For the complete collection, see [Hugging Face's roocode collection](https://huggingface.co/collections/roocode).
-
-**Default:** `meta-llama/Llama-3.3-70B-Instruct` if no model is selected.
-
-**Pro tip:** Both the model and provider dropdowns are searchable for quick selection.
+For the complete, up-to-date model collection, see [Hugging Face's roocode collection](https://huggingface.co/collections/roocode).
 
 ---
 
diff --git a/docs/providers/lmstudio.md b/docs/providers/lmstudio.md
@@ -25,14 +25,7 @@ Roo Code supports running models locally using LM Studio.  LM Studio provides a
 ## Setting Up LM Studio
 
 1.  **Download and Install LM Studio:** Download LM Studio from the [LM Studio website](https://lmstudio.ai/).
-2.  **Download a Model:**  Use the LM Studio interface to search for and download a model in GGUF format.
-
-    **Recommended for coding with Roo Code:**
-    *   CodeLlama models (`codellama:13b-code` or `codellama:34b-code`)
-    *   Qwen Coder models
-    *   DeepSeek Coder models
-    
-    Browse all available models in the LM Studio search interface or at [Hugging Face](https://huggingface.co/models?library=gguf).
+2.  **Download a Model:**  Use the LM Studio interface to search for and download a model in GGUF format. Browse all available models in the LM Studio search interface or at [Hugging Face](https://huggingface.co/models?library=gguf).
 3.  **Start the Local Server:**
     *   Open LM Studio.
     *   Click the **"Local Server"** tab (the icon looks like `<->`).
diff --git a/docs/providers/mistral.md b/docs/providers/mistral.md
@@ -37,14 +37,6 @@ Roo Code supports all models available through Mistral AI's API.
 
 For the complete, up-to-date model list and capabilities, see [Mistral's model documentation](https://docs.mistral.ai/getting-started/models/models_overview/).
 
-**Recommended for Roo Code:**
-- **Codestral** - Best for code generation and interaction tasks (specialized coding model)
-- **Mistral Large** - Better for complex reasoning and analysis
-- **Pixtral** - Best when you need vision/image support
-- **Ministral models** - Faster and more cost-effective for simpler tasks
-
-**Note:** Mistral models have different default temperatures (0.3-0.7). Roo Code defaults to 0.0, so consider [adjusting temperature](/features/model-temperature) for more varied outputs.
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/ollama.md b/docs/providers/ollama.md
@@ -31,14 +31,7 @@ Roo Code supports running models locally using Ollama. This provides privacy, of
     ollama serve
     ```
 
-2.  **Download a Model:**  Browse [Ollama's model library](https://ollama.com/library) for all available models.
-
-    **Recommended for coding with Roo Code:**
-    *   `qwen2.5-coder:32b` - Best balance of quality and resource usage
-    *   `codellama:13b-code` or `codellama:34b-code` - Strong coding-specific alternatives
-    *   `deepseek-coder:6.7b-base` - Good for resource-limited machines
-
-    To download a model, run:
+2.  **Download a Model:**  Browse [Ollama's model library](https://ollama.com/library) for all available models. To download a model, run:
 
     ```bash
     ollama pull <model_name>
diff --git a/docs/providers/openai.md b/docs/providers/openai.md
@@ -40,12 +40,6 @@ Roo Code supports all models available through OpenAI's API.
 
 For the complete, up-to-date model list and capabilities, see [OpenAI's models documentation](https://platform.openai.com/docs/models).
 
-**Recommended for Roo Code:**
-- **GPT-5 models** - Best for coding and agentic tasks (default: `gpt-5.1`)
-- **GPT-5-Codex** - Specialized for code generation with 400K context window and prompt caching
-- **o-series models** - Better for complex reasoning and problem-solving tasks
-- **Mini/Nano variants** - Faster and more cost-effective for well-defined tasks
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/openrouter.md b/docs/providers/openrouter.md
@@ -35,8 +35,6 @@ Roo Code automatically fetches all available models from OpenRouter's API (100+
 
 For the complete, up-to-date model list with pricing and capabilities, see [OpenRouter's models page](https://openrouter.ai/models).
 
-**Key advantage:** Access multiple AI providers through a single API without managing separate keys for each.
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/qwen-code.md b/docs/providers/qwen-code.md
@@ -37,8 +37,6 @@ Both Qwen3 Coder models feature massive 1M context windows and 65K max output to
 - **qwen3-coder-plus** - High-performance coding model (default)
 - **qwen3-coder-flash** - Speed-optimized variant
 
-**Currently free** with 2,000 requests/day and 60 requests/minute during promotional period.
-
 ---
 
 ## Configuration
diff --git a/docs/providers/requesty.md b/docs/providers/requesty.md
@@ -34,8 +34,6 @@ Roo Code automatically fetches all available models from Requesty's API (150+ mo
 
 For the complete, up-to-date model list with pricing, see [Requesty's model list](https://app.requesty.ai/router/list).
 
-**Key advantage:** Single API key for 150+ models across all major providers, with unified billing and cost tracking.
-
 ---
 
 ## Configuration in Roo Code
diff --git a/docs/providers/roo-code-cloud.md b/docs/providers/roo-code-cloud.md
diff --git a/docs/providers/sambanova.md b/docs/providers/sambanova.md
diff --git a/docs/providers/unbound.md b/docs/providers/unbound.md
diff --git a/docs/providers/vercel-ai-gateway.md b/docs/providers/vercel-ai-gateway.md
diff --git a/docs/providers/vertex.md b/docs/providers/vertex.md
diff --git a/docs/providers/xai.md b/docs/providers/xai.md
diff --git a/docs/providers/zai.md b/docs/providers/zai.md
