RooCodeInc · hannesrudolph · Sep 5, 2025 · Sep 5, 2025 · Sep 5, 2025 · Sep 5, 2025
@@ -0,0 +1,90 @@
+---
+sidebar_label: DeepInfra
+description: Configure DeepInfra's high-performance AI models in Roo Code. Access Qwen Coder, Llama, and other open-source models with prompt caching and vision capabilities.
+keywords:
+  - deepinfra
+  - deep infra
+  - roo code
+  - api provider
+  - qwen coder
+  - llama models
+  - prompt caching
+  - vision models
+  - open source ai
+image: /img/social-share.jpg
+---
+
+# Using DeepInfra With Roo Code
+
+DeepInfra provides cost-effective access to high-performance open-source models with features like prompt caching, vision support, and specialized coding models. Their infrastructure offers low latency and automatic load balancing across global edge locations.
+
+**Website:** [https://deepinfra.com/](https://deepinfra.com/)
+
+---
+
+## Getting an API Key
+
+1. **Sign Up/Sign In:** Go to [DeepInfra](https://deepinfra.com/). Create an account or sign in.
+2. **Navigate to API Keys:** Access the API keys section in your dashboard.
+3. **Create a Key:** Generate a new API key. Give it a descriptive name (e.g., "Roo Code").
+4. **Copy the Key:** **Important:** Copy the API key immediately. Store it securely.
+
+---
+
+## Supported Models
+
+Roo Code dynamically fetches available models from DeepInfra's API. The default model is:
+
+* `Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo` (256K context, optimized for coding)
+
+Common models available include:
+
+* **Coding Models:** Qwen Coder series, specialized for programming tasks
+* **General Models:** Llama 3.1, Mixtral, and other open-source models
+* **Vision Models:** Models with image understanding capabilities
+* **Reasoning Models:** Models with advanced reasoning support
+
+Browse the full catalog at [deepinfra.com/models](https://deepinfra.com/models).
+
+---
+
+## 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.
@@ -19,6 +19,7 @@ image: /img/social-share.jpg
 
 ### Version 3.26
 
+*   [3.26.7](/update-notes/v3.26.7) (2025-09-05)
 *   [3.26.6](/update-notes/v3.26.6) (2025-09-03)
 *   [3.26.5](/update-notes/v3.26.5) (2025-09-03)
 *   [3.26.4](/update-notes/v3.26.4) (2025-09-01)

@@ -0,0 +1,63 @@
+---
+description: Enhanced Kimi K2 models with 256K+ context windows, OpenAI service tiers for flexible pricing, and DeepInfra as a new provider with 100+ models.
+keywords:
+  - roo code 3.26.7
+  - kimi k2 models
+  - openai service tiers
+  - deepinfra provider
+  - bug fixes
+image: /img/social-share.jpg
+---
+
+# Roo Code 3.26.7 Release Notes (2025-09-05)
+
+This release brings enhanced Kimi K2 models with massive context windows, OpenAI service tier selection, and DeepInfra as a new provider offering 100+ models.
+
+## Kimi K2-0905: Moonshot's Latest Open Source Model is Live in Roo Code
+
+We've upgraded to the latest Kimi K2-0905 models across multiple providers (thanks CellenLee!) ([#7663](https://github.com/RooCodeInc/Roo-Code/pull/7663), [#7693](https://github.com/RooCodeInc/Roo-Code/pull/7693)):
+
+K2-0905 comes with three major upgrades:
+- **256K Context Window**: Massive context supporting up to 256K-262K tokens, doubling the previous limit for processing much larger documents and conversations
+- **Improved Tool Calling**: Enhanced function calling and tool use capabilities for better agentic workflows
+- **Enhanced Front-end Development**: Superior HTML, CSS, and JavaScript generation with modern framework support
+
+Available through Groq, Moonshot, and Fireworks providers. These models excel at handling large codebases, long conversations, and complex multi-file operations.
+
+## OpenAI Service Tiers
+
+We've added support for OpenAI's new Responses API service tiers ([#7646](https://github.com/RooCodeInc/Roo-Code/pull/7646)):
+
+- **Standard Tier**: Default tier with regular pricing
+- **Flex Tier**: 50% discount with slightly longer response times for non-urgent tasks
+- **Priority Tier**: Faster response times for time-critical operations
+
+Select your preferred tier directly in the UI based on your needs and budget. This gives you more control over costs while maintaining access to OpenAI's powerful models.
+
+> **📚 Documentation**: See [OpenAI Provider Guide](/providers/openai) for detailed tier comparison and pricing.
+
+## DeepInfra Provider
+
+DeepInfra is now available as a model provider (thanks Thachnh!) ([#7677](https://github.com/RooCodeInc/Roo-Code/pull/7677)):
+
+- **100+ Models**: Access to a vast selection of open-source and frontier models
+- **Competitive Pricing**: Very cost-effective rates compared to other providers
+- **Automatic Prompt Caching**: Built-in prompt caching for supported models like Qwen3 Coder
+- **Fast Inference**: Optimized infrastructure for quick response times
+
+DeepInfra is an excellent choice for developers looking for variety and value in their AI model selection.
+
+> **📚 Documentation**: See [DeepInfra Provider Setup](/providers/deepinfra) to get started.
+
+## QOL Improvements
+
+* **Shell Security**: Added shell executable allowlist validation with platform-specific fallbacks for improved command execution safety ([#7681](https://github.com/RooCodeInc/Roo-Code/pull/7681))
+
+## Bug Fixes
+
+* **MCP Tool Validation**: Roo now validates MCP tool existence before execution and shows helpful error messages with available tools (thanks R-omk!) ([#7632](https://github.com/RooCodeInc/Roo-Code/pull/7632))
+* **OpenAI API Key Errors**: Clear error messages now display when API keys contain invalid characters instead of cryptic ByteString errors (thanks A0nameless0man!) ([#7586](https://github.com/RooCodeInc/Roo-Code/pull/7586))
+* **Follow-up Questions**: Fixed countdown timer incorrectly reappearing in task history for already answered follow-up questions (thanks XuyiK!) ([#7686](https://github.com/RooCodeInc/Roo-Code/pull/7686))
+* **Moonshot Token Limit**: Resolved issue where Moonshot models were incorrectly limited to 1024 tokens, now properly respects configured limits (thanks wangxiaolong100, greyishsong!) ([#7673](https://github.com/RooCodeInc/Roo-Code/pull/7673))
+* **Zsh Command Safety**: Improved handling of zsh process substitution and glob qualifiers to prevent auto-execution of potentially dangerous commands ([#7658](https://github.com/RooCodeInc/Roo-Code/pull/7658), [#7667](https://github.com/RooCodeInc/Roo-Code/pull/7667))
+* **Traditional Chinese Localization**: Fixed typo in zh-TW locale text (thanks PeterDaveHello!) ([#7672](https://github.com/RooCodeInc/Roo-Code/pull/7672))
@@ -94,8 +94,32 @@ PRs: [#7474](https://github.com/RooCodeInc/Roo-Code/pull/7474), [#7492](https://
 
 > **📚 Documentation**: See [Image Generation - Editing Existing Images](/features/image-generation#editing-existing-images) for transformation examples.
 
+### Kimi K2-0905: Moonshot's Latest Open Source Model is Live in Roo Code
+
+We've upgraded to the latest Kimi K2-0905 models across multiple providers (thanks CellenLee!) ([#7663](https://github.com/RooCodeInc/Roo-Code/pull/7663), [#7693](https://github.com/RooCodeInc/Roo-Code/pull/7693)):
+
+K2-0905 comes with three major upgrades:
+- **256K Context Window**: Massive context supporting up to 256K-262K tokens, doubling the previous limit for processing much larger documents and conversations
+- **Improved Tool Calling**: Enhanced function calling and tool use capabilities for better agentic workflows
+- **Enhanced Front-end Development**: Superior HTML, CSS, and JavaScript generation with modern framework support
+
+Available through Groq, Moonshot, and Fireworks providers. These models excel at handling large codebases, long conversations, and complex multi-file operations.
+
+### OpenAI Service Tiers
+
+We've added support for OpenAI's new Responses API service tiers ([#7646](https://github.com/RooCodeInc/Roo-Code/pull/7646)):
+
+- **Standard Tier**: Default tier with regular pricing
+- **Flex Tier**: 50% discount with slightly longer response times for non-urgent tasks
+- **Priority Tier**: Faster response times for time-critical operations
+
+Select your preferred tier directly in the UI based on your needs and budget. This gives you more control over costs while maintaining access to OpenAI's powerful models.
+
+> **📚 Documentation**: See [OpenAI Provider Guide](/providers/openai) for detailed tier comparison and pricing.
+
 ### Provider Updates
 
+* **DeepInfra Provider**: DeepInfra is now available as a model provider with 100+ open-source and frontier models, competitive pricing, and automatic prompt caching for supported models like Qwen3 Coder (thanks Thachnh!) ([#7677](https://github.com/RooCodeInc/Roo-Code/pull/7677))
 * **Kimi K2 Turbo Model**: Added support for the high-speed Kimi K2 Turbo model with 60-100 tokens/sec processing and a 131K token context window (thanks wangxiaolong100!) ([#7593](https://github.com/RooCodeInc/Roo-Code/pull/7593))
 * **Qwen3 235B Thinking Model**: Added support for Qwen3-235B-A22B-Thinking-2507 model with an impressive 262K context window, enabling processing of extremely long documents and large codebases in a single request through the Chutes provider (thanks mohammad154, apple-techie!) ([#7578](https://github.com/RooCodeInc/Roo-Code/pull/7578))
 * **Ollama Turbo Mode**: Added API key support for Turbo mode, enabling faster model execution with datacenter-grade hardware (thanks LivioGama!) ([#7425](https://github.com/RooCodeInc/Roo-Code/pull/7425))
@@ -104,6 +128,7 @@ PRs: [#7474](https://github.com/RooCodeInc/Roo-Code/pull/7474), [#7492](https://
 
 ### QOL Improvements
 
+* **Shell Security**: Added shell executable allowlist validation with platform-specific fallbacks for improved command execution safety ([#7681](https://github.com/RooCodeInc/Roo-Code/pull/7681))
 * **Settings Scroll Position**: Settings tabs now remember their individual scroll positions when switching between them (thanks DC-Dancao!) ([#7587](https://github.com/RooCodeInc/Roo-Code/pull/7587))
 * **MCP Resource Auto-Approval**: MCP resource access requests are now automatically approved when auto-approve is enabled, eliminating manual approval steps and enabling smoother automation workflows (thanks m-ibm!) ([#7606](https://github.com/RooCodeInc/Roo-Code/pull/7606))
 * **Message Queue Performance**: Improved message queueing reliability and performance by moving the queue management to the extension host, making the interface more stable ([#7604](https://github.com/RooCodeInc/Roo-Code/pull/7604))
@@ -122,6 +147,12 @@ PRs: [#7474](https://github.com/RooCodeInc/Roo-Code/pull/7474), [#7492](https://
 
 ### Bug Fixes
 
+* **MCP Tool Validation**: Roo now validates MCP tool existence before execution and shows helpful error messages with available tools (thanks R-omk!) ([#7632](https://github.com/RooCodeInc/Roo-Code/pull/7632))
+* **OpenAI API Key Errors**: Clear error messages now display when API keys contain invalid characters instead of cryptic ByteString errors (thanks A0nameless0man!) ([#7586](https://github.com/RooCodeInc/Roo-Code/pull/7586))
+* **Follow-up Questions**: Fixed countdown timer incorrectly reappearing in task history for already answered follow-up questions (thanks XuyiK!) ([#7686](https://github.com/RooCodeInc/Roo-Code/pull/7686))
+* **Moonshot Token Limit**: Resolved issue where Moonshot models were incorrectly limited to 1024 tokens, now properly respects configured limits (thanks wangxiaolong100, greyishsong!) ([#7673](https://github.com/RooCodeInc/Roo-Code/pull/7673))
+* **Zsh Command Safety**: Improved handling of zsh process substitution and glob qualifiers to prevent auto-execution of potentially dangerous commands ([#7658](https://github.com/RooCodeInc/Roo-Code/pull/7658), [#7667](https://github.com/RooCodeInc/Roo-Code/pull/7667))
+* **Traditional Chinese Localization**: Fixed typo in zh-TW locale text (thanks PeterDaveHello!) ([#7672](https://github.com/RooCodeInc/Roo-Code/pull/7672))
 * **Tool Approval Fix**: Fixed an error that occurred when using insert_content and search_and_replace tools on write-protected files - these tools now handle file protection correctly ([#7649](https://github.com/RooCodeInc/Roo-Code/pull/7649))
 * **Configurable Embedding Batch Size**: Fixed an issue where users with API providers having stricter batch limits couldn't use code indexing. You can now configure the embedding batch size (1-2048, default: 400) to match your provider's limits (thanks BenLampson!) ([#7464](https://github.com/RooCodeInc/Roo-Code/pull/7464))
 * **OpenAI-Native Cache Reporting**: Fixed cache usage statistics and cost calculations when using the OpenAI-Native provider with cached content ([#7602](https://github.com/RooCodeInc/Roo-Code/pull/7602))

@@ -164,6 +164,7 @@ const sidebars: SidebarsConfig = {
         'providers/claude-code',
         'providers/bedrock',
         'providers/cerebras',
+        'providers/deepinfra',
         'providers/deepseek',
         'providers/doubao',
         'providers/featherless',
@@ -221,6 +222,7 @@ const sidebars: SidebarsConfig = {
           label: '3.26',
           items: [
             { type: 'doc', id: 'update-notes/v3.26', label: '3.26 Combined' },
+            { type: 'doc', id: 'update-notes/v3.26.7', label: '3.26.7' },
             { type: 'doc', id: 'update-notes/v3.26.6', label: '3.26.6' },
             { type: 'doc', id: 'update-notes/v3.26.5', label: '3.26.5' },
             { type: 'doc', id: 'update-notes/v3.26.4', label: '3.26.4' },