Kilo-Org · emilieschario · Nov 19, 2025
diff --git a/apps/kilocode-docs/docs/providers/cerebras.md b/apps/kilocode-docs/docs/providers/cerebras.md
@@ -0,0 +1,39 @@
+---
+sidebar_label: Cerebras
+---
+
+# Using Cerebras With Kilo Code
+
+Cerebras is known for their ultra-fast AI inference powered by the Cerebras CS-3 chip, the world's largest and fastest AI accelerator. Their platform delivers exceptional inference speeds for large language models, making them ideal for interactive development workflows.
+
+**Website:** [https://cerebras.ai/](https://cerebras.ai/)
+
+## Getting an API Key
+
+1. **Sign Up/Sign In:** Go to the [Cerebras Cloud Platform](https://cloud.cerebras.ai/). Create an account or sign in.
+2. **Navigate to API Keys:** Access the API Keys section in your account dashboard.
+3. **Create a Key:** Click to generate a new API key. Give it a descriptive name (e.g., "Kilo Code").
+4. **Copy the Key:** **Important:** Copy the API key _immediately_. Store it securely.
+
+## Supported Models
+
+Kilo Code supports the following Cerebras models:
+
+- `gpt-oss-120b` (Default) – High-performance open-source model optimized for fast inference
+- `zai-glm-4.6` – Advanced GLM model with enhanced reasoning capabilities
+
+Refer to the [Cerebras documentation](https://docs.cerebras.ai/) for detailed information on model capabilities and performance characteristics.
+
+## Configuration in Kilo Code
+
+1. **Open Kilo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Kilo Code panel.
+2. **Select Provider:** Choose "Cerebras" from the "API Provider" dropdown.
+3. **Enter API Key:** Paste your Cerebras API key into the "Cerebras API Key" field.
+4. **Select Model:** Choose your desired model from the "Model" dropdown.
+
+## Tips and Notes
+
+- **Inference Speed:** Cerebras models deliver some of the fastest inference speeds available, reducing wait times during development.
+- **Open Source Models:** Many Cerebras models are based on open-source architectures, optimized for their custom hardware.
+- **Cost Efficiency:** Fast inference can lead to better cost efficiency for interactive use cases.
+- **Pricing:** Refer to the Cerebras platform for current pricing information and available plans.
diff --git a/apps/kilocode-docs/docs/providers/inception.md b/apps/kilocode-docs/docs/providers/inception.md
@@ -0,0 +1,35 @@
+---
+sidebar_label: Inception
+---
+
+# Using Inception With Kilo Code
+
+Inception provides access to cutting-edge AI models with a focus on performance and reliability. Their infrastructure is designed for enterprise-grade applications requiring consistent, high-quality outputs.
+
+**Website:** [https://inception.ai](https://inception.ai)
+
+## Getting an API Key
+
+1. **Sign Up/Sign In:** Go to the [Inception Platform](https://platform.inception.ai). Create an account or sign in.
+2. **Navigate to API Keys:** Access the API Keys section in your account settings.
+3. **Create a Key:** Click "Create new API key". Give your key a descriptive name (e.g., "Kilo Code").
+4. **Copy the Key:** **Important:** Copy the API key _immediately_. You will not be able to see it again. Store it securely.
+
+## Supported Models
+
+Kilo Code supports Inception's available models. Model selection and capabilities may vary based on your account tier.
+
+Refer to the [Inception documentation](https://docs.inception.ai) for the most up-to-date list of supported models and their specific capabilities.
+
+## Configuration in Kilo Code
+
+1. **Open Kilo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Kilo Code panel.
+2. **Select Provider:** Choose "Inception" from the "API Provider" dropdown.
+3. **Enter API Key:** Paste your Inception API key into the "Inception API Key" field.
+4. **Select Model:** Choose your desired model from the "Model" dropdown.
+
+## Tips and Notes
+
+- **Enterprise Focus:** Inception is designed for production-grade AI applications with emphasis on reliability and consistency.
+- **Pricing:** Refer to the Inception platform for current pricing details and available subscription options.
+- **Support:** Enterprise customers have access to dedicated support channels for technical assistance.
diff --git a/apps/kilocode-docs/docs/providers/moonshot.md b/apps/kilocode-docs/docs/providers/moonshot.md
@@ -0,0 +1,41 @@
+---
+sidebar_label: Moonshot.ai
+---
+
+# Using Moonshot.ai With Kilo Code
+
+Moonshot.ai is a Chinese AI company known for their **Kimi** models featuring ultra-long context windows (up to 200K tokens) and advanced reasoning capabilities. Their K2-Thinking model delivers extended thinking and problem-solving abilities.
+
+**Website:** [https://www.moonshot.cn/](https://www.moonshot.cn/)
+
+## Getting an API Key
+
+1. **Sign Up/Sign In:** Go to the [Moonshot.ai Platform](https://platform.moonshot.cn/). Create an account or sign in.
+2. **Navigate to API Keys:** Access the API Keys section in your account dashboard.
+3. **Create a Key:** Click to generate a new API key. Give it a descriptive name (e.g., "Kilo Code").
+4. **Copy the Key:** **Important:** Copy the API key _immediately_. Store it securely.
+
+## Supported Models
+
+Kilo Code supports the following Moonshot.ai models:
+
+- `moonshot-v1-8k` – General-purpose model with 8K context
+- `moonshot-v1-32k` – Extended context model with 32K tokens
+- `moonshot-v1-128k` – Long-context model with 128K tokens
+- `kimi-k2-thinking` – Advanced reasoning model with extended thinking capabilities
+
+Refer to the [Moonshot.ai documentation](https://platform.moonshot.cn/docs) for detailed information on each model's capabilities and pricing.
+
+## Configuration in Kilo Code
+
+1. **Open Kilo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Kilo Code panel.
+2. **Select Provider:** Choose "Moonshot.ai" from the "API Provider" dropdown.
+3. **Enter API Key:** Paste your Moonshot.ai API key into the "Moonshot.ai API Key" field.
+4. **Select Model:** Choose your desired model from the "Model" dropdown.
+
+## Tips and Notes
+
+- **Ultra-Long Context:** Kimi models excel at handling large codebases and complex projects with their extended context windows.
+- **Reasoning Capabilities:** The K2-Thinking variant provides enhanced problem-solving through extended reasoning chains.
+- **Language Support:** Kimi models have strong support for both English and Chinese languages.
+- **Pricing:** Refer to the Moonshot.ai platform for current pricing information on different models.
diff --git a/apps/kilocode-docs/sidebars.ts b/apps/kilocode-docs/sidebars.ts
@@ -53,28 +53,31 @@ const sidebars: SidebarsConfig = {
 							items: [
 								"providers/anthropic",
 								"providers/bedrock",
+								"providers/cerebras", // kilocode_change
 								"providers/chutes-ai",
 								"providers/claude-code",
 								"providers/deepseek",
 								"providers/fireworks",
-								"providers/synthetic", // kilocode_change
-								"providers/vertex",
-								"providers/glama",
 								"providers/gemini",
+								"providers/glama",
 								"providers/groq",
 								"providers/human-relay",
+								"providers/inception", // kilocode_change
 								"providers/lmstudio",
-								"providers/minimax",
+								"providers/minimax", // kilocode_change (M2 model update)
 								"providers/mistral",
+								"providers/moonshot", // kilocode_change
 								"providers/ollama",
 								"providers/openai",
 								"providers/openai-compatible",
 								"providers/openrouter",
 								"providers/ovhcloud", // kilocode_change
 								"providers/requesty",
+								"providers/synthetic", // kilocode_change
 								"providers/unbound",
 								"providers/v0",
 								"providers/vercel-ai-gateway",
+								"providers/vertex",
 								"providers/virtual-quota-fallback",
 								"providers/vscode-lm",
 								"providers/xai",