continuedev · sestinj · Jan 15, 2026 · Jan 15, 2026
@@ -13,18 +13,18 @@ description: "Learn how to use Continue's AI-powered code autocomplete feature w
 
 Autocomplete provides inline code suggestions as you type. To enable it, simply click the "Continue" button in the status bar at the bottom right of your IDE or ensure the "Enable Tab Autocomplete" option is checked in your IDE settings.
 
-### Accepting a full suggestion
+### Accepting a Full Suggestion
 
 Accept a full suggestion by pressing `Tab`
 
-### Rejecting a full suggestion
+### Rejecting a Full Suggestion
 
 Reject a full suggestion with `Esc`
 
-### Partially accepting a suggestion
+### Partially Accepting a Suggestion
 
 For more granular control, use `cmd/ctrl` + `→` to accept parts of the suggestion word-by-word.
 
-### Forcing a suggestion (VS Code)
+### Forcing a Suggestion (VS Code)
 
 If you want to trigger a suggestion immediately without waiting, or if you've dismissed a suggestion and want a new one, you can force it by using the keyboard shortcut **`cmd/ctrl` + `alt` + `space`**.
@@ -15,7 +15,7 @@ sidebarTitle: "Overview"
   Automate tedious tasks.
 </Tip>
 
-## Get started in 30 seconds
+## Get Started in 30 Seconds
 
 Prerequisites:
 
@@ -226,7 +226,7 @@ cn -p "Scan the codebase for potential security vulnerabilities"
 
 </CodeGroup>
 
-## Next steps
+## Next Steps
 
 <CardGroup cols={3}>
   <Card title="CLI Quickstart" href="/cli/quick-start">

@@ -7,7 +7,7 @@ sidebarTitle: "Prompts"
 
 Prompts are included as user messages and are especially useful as instructions for repetitive and/or complex tasks.
 
-## Slash commands
+## Slash Commands
 
 By setting `invokable` to `true`, you make the markdown file a prompt, which will be available when you type <kbd>/</kbd> in Chat, Plan, and Agent mode.
 

@@ -5,7 +5,7 @@ description: "Configure Cohere's AI models with Continue, including setup for Co
 
 Before using Cohere, visit the [Cohere dashboard](https://dashboard.cohere.com/api-keys) to create an API key.
 
-## Chat model
+## Chat Model
 
 We recommend configuring **Command A** as your chat model.
 
@@ -39,13 +39,13 @@ We recommend configuring **Command A** as your chat model.
   </Tab>
 </Tabs>
 
-## Autocomplete model
+## Autocomplete Model
 
 Cohere currently does not offer any autocomplete models.
 
 [Click here](../../model-roles/autocomplete) to see a list of autocomplete model providers.
 
-## Embeddings model
+## Embeddings Model
 
 We recommend configuring **embed-v4.0** as your embeddings model.
 
@@ -78,7 +78,7 @@ We recommend configuring **embed-v4.0** as your embeddings model.
   </Tab>
 </Tabs>
 
-## Reranking model
+## Reranking Model
 
 We recommend configuring **rerank-v3.5** as your reranking model.
 

@@ -11,7 +11,7 @@ To get an API key, login to the Function Network Developer Platform. If you don'
 
 </Info>
 
-## Chat model
+## Chat Model
 
 Function Network supports a number of models for chat. We recommend using LLama 3.1 70b or Qwen2.5-Coder-32B-Instruct.
 
@@ -49,7 +49,7 @@ Function Network supports a number of models for chat. We recommend using LLama
 
 [Click here](https://docs.function.network/models-supported/chat-and-code-completion) to see a list of chat model providers.
 
-## Autocomplete model
+## Autocomplete Model
 
 Function Network supports a number of models for autocomplete. We recommend using Llama 3.1 8b or Qwen2.5-Coder-1.5B.
 
@@ -83,7 +83,7 @@ Function Network supports a number of models for autocomplete. We recommend usin
   </Tab>
 </Tabs>
 
-## Embeddings model
+## Embeddings Model
 
 Function Network supports a number of models for embeddings. We recommend using baai/bge-base-en-v1.5.
 
@@ -118,6 +118,6 @@ Function Network supports a number of models for embeddings. We recommend using
 
 [Click here](https://docs.function.network/models-supported/embeddings) to see a list of embeddings model providers.
 
-## Reranking model
+## Reranking Model
 
 Function Network currently does not offer any reranking models.
@@ -55,7 +55,7 @@ or
    </Tab>
 </Tabs>
 
-## Embeddings model
+## Embeddings Model
 
 We recommend configuring **morph-embedding-v2** as your embeddings model.
 
@@ -90,7 +90,7 @@ We recommend configuring **morph-embedding-v2** as your embeddings model.
   </Tab>
 </Tabs>
 
-## Reranking model
+## Reranking Model
 
 We recommend configuring **morph-rerank-v2** as your reranking model.
 

@@ -5,11 +5,11 @@ description: "Configure Nebius AI Studio with Continue to access their language
 
 You can get an API key from the [Nebius AI Studio API keys page](https://studio.nebius.ai/settings/api-keys)
 
-## Availible models
+## Available Models
 
 Available models can be found on the [Nebius AI Studio models page](https://studio.nebius.ai/models/text2text)
 
-## Chat model
+## Chat Model
 
 <Tabs>
   <Tab title="YAML">
@@ -41,7 +41,7 @@ Available models can be found on the [Nebius AI Studio models page](https://stud
   </Tab>
 </Tabs>
 
-## Embeddings model
+## Embeddings Model
 
 Available models can be found on the [Nebius AI Studio embeddings page](https://studio.nebius.ai/models/embedding)
 

@@ -12,7 +12,7 @@ OVHcloud AI Endpoints is a serverless inference API that provides access to a cu
   page](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/).
 </Info>
 
-## Chat model
+## Chat Model
 
 We recommend configuring **Qwen2.5-Coder-32B-Instruct** as your chat model.
 Check our [catalog](https://endpoints.ai.cloud.ovh.net/catalog) to see all of our models hsoted on AI Endpoints.
@@ -47,7 +47,7 @@ Check our [catalog](https://endpoints.ai.cloud.ovh.net/catalog) to see all of ou
     </Tab>
 </Tabs>
 
-## Embeddings model
+## Embeddings Model
 
 We recommend configuring **bge-multilingual-gemma2** as your embeddings model.
 

@@ -12,7 +12,7 @@ description: "Configure Scaleway Generative APIs with Continue to access AI mode
   here](https://www.scaleway.com/en/docs/ai-data/generative-apis/quickstart/).
 </Info>
 
-## Chat model
+## Chat Model
 
 We recommend configuring **Qwen2.5-Coder-32B-Instruct** as your chat model.
 [Click here](https://www.scaleway.com/en/docs/ai-data/generative-apis/reference-content/supported-models/) to see the list of available chat models.
@@ -47,13 +47,13 @@ We recommend configuring **Qwen2.5-Coder-32B-Instruct** as your chat model.
     </Tab>
 </Tabs>
 
-## Autocomplete model
+## Autocomplete Model
 
 Scaleway currently does not offer any autocomplete models.
 
 [Click here](../../model-roles/autocomplete) to see a list of autocomplete model providers.
 
-## Embeddings model
+## Embeddings Model
 
 We recommend configuring **BGE-Multilingual-Gemma2** as your embeddings model.
 

@@ -8,7 +8,7 @@ description: "Configure SiliconFlow with Continue to access their AI model platf
   Cloud](https://cloud.siliconflow.cn/account/ak).
 </Info>
 
-## Chat model
+## Chat Model
 
 We recommend configuring **Qwen/Qwen2.5-Coder-32B-Instruct** as your chat model.
 
@@ -44,7 +44,7 @@ We recommend configuring **Qwen/Qwen2.5-Coder-32B-Instruct** as your chat model.
     </Tab>
 </Tabs>
 
-## Autocomplete model
+## Autocomplete Model
 
 We recommend configuring **Qwen/Qwen2.5-Coder-7B-Instruct** as your autocomplete model.
 
@@ -86,10 +86,10 @@ We recommend configuring **Qwen/Qwen2.5-Coder-7B-Instruct** as your autocomplete
     </Tab>
 </Tabs>
 
-## Embeddings model
+## Embeddings Model
 
 SiliconFlow provide some embeddings models. [Click here](https://siliconflow.cn/models) to see a list of embeddings models.
 
-## Reranking model
+## Reranking Model
 
 SiliconFlow provide some reranking models. [Click here](https://siliconflow.cn/models) to see a list of reranking models.
@@ -9,7 +9,7 @@ vLLM is an open-source library for fast LLM inference which typically is used to
 vllm serve meta-llama/Meta-Llama-3.1-8B-Instruct
 ```
 
-## Chat model
+## Chat Model
 
 We recommend configuring **Llama3.1 8B** as your chat model.
 
@@ -43,7 +43,7 @@ We recommend configuring **Llama3.1 8B** as your chat model.
     </Tab>
 </Tabs>
 
-## Autocomplete model
+## Autocomplete Model
 
 We recommend configuring **Qwen2.5-Coder 1.5B** as your autocomplete model.
 
@@ -77,7 +77,7 @@ We recommend configuring **Qwen2.5-Coder 1.5B** as your autocomplete model.
    </Tab>
 </Tabs>
 
-## Embeddings model
+## Embeddings Model
 
 We recommend configuring **Nomic Embed Text** as your embeddings model.
 
@@ -110,7 +110,7 @@ We recommend configuring **Nomic Embed Text** as your embeddings model.
    </Tab>
 </Tabs>
 
-## Reranking model
+## Reranking Model
 
 Continue automatically handles vLLM's response format (which uses `results` instead of `data`).
 

@@ -157,7 +157,7 @@ If you prefer to use a model from [Google](../model-providers/top-level/gemini),
   </Tab>
 </Tabs>
 
-## Local, offline experience
+## Local, Offline Experience
 
 For the best local, offline Chat experience, you will want to use a model that is large but fast enough on your machine.
 

@@ -48,7 +48,7 @@ If you are using VS Code and require requests to be made through a proxy, you ar
 
 Continue can be used in [code-server](https://coder.com/), but if you are running across an error in the logs that includes "This is likely because the editor is not running in a secure context", please see [their documentation on securely exposing code-server](https://coder.com/docs/code-server/latest/guide#expose-code-server).
 
-## Changes to configs not showing in VS Code
+## Changes to Configs Not Showing in VS Code
 
 If you've made changes to a config (adding, modifying, or removing it) but the changes aren't appearing in the Continue extension in VS Code, try reloading the VS Code window:
 

@@ -10,7 +10,7 @@ It provides a battle-tested agent loop so you can simply plug in your model, rul
 
 ![cn](/images/cn-demo.gif)
 
-## Quick start
+## Quick Start
 
 <Info>
   Make sure you have [Node.js 18 or higher
-Original file line number
+Diff line change
@@ Expand Up @@
       </Tab>
     </Tabs>
-    ## Local, offline experience
+    ## Local, Offline Experience
     For the best local, offline Chat experience, you will want to use a model that is large but fast enough on your machine.
@@ Expand Down @@