Continue.dev - Eden AI Documentation

Configure Continue.dev, the open-source AI code assistant, to use Eden AI for access to 500+ models.

Overview

Continue.dev is an open-source autopilot for VS Code and JetBrains IDEs. By connecting it to Eden AI, you get:

500+ models: Access OpenAI, Anthropic, Google, Cohere, and more
Cost savings: Leverage Eden AI’s competitive pricing
Provider flexibility: Switch models instantly without changing configuration

Installation

Install Continue.dev from your IDE marketplace:

VS Code

Open VS Code
Go to Extensions (Ctrl+Shift+X / Cmd+Shift+X)
Search for “Continue”
Click Install

JetBrains IDEs

Open your JetBrains IDE (IntelliJ, PyCharm, etc.)
Go to Plugins (Ctrl+Alt+S / Cmd+,)
Search for “Continue”
Click Install

Configuration

Configure Continue to use Eden AI’s OpenAI-compatible endpoint.

Step 1: Open Configuration

In VS Code or JetBrains:

Click the Continue icon in the sidebar
Click the gear icon (⚙️) to open settings
This opens ~/.continue/config.json

Step 2: Configure Eden AI

Replace the configuration with:

{
  "models": [
    {
      "title": "Claude 3.5 Sonnet",
      "provider": "openai",
      "model": "anthropic/claude-sonnet-4-5",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3"
    },
    {
      "title": "GPT-4",
      "provider": "openai",
      "model": "openai/gpt-4",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3"
    },
    {
      "title": "Gemini Pro",
      "provider": "openai",
      "model": "google/gemini-2.5-flash",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3"
    }
  ],
  "tabAutocompleteModel": {
    "title": "GPT-3.5 Turbo",
    "provider": "openai",
    "model": "openai/gpt-3.5-turbo",
    "apiKey": "YOUR_EDEN_AI_API_KEY",
    "apiBase": "https://api.edenai.run/v3"
  },
  "embeddingsProvider": {
    "provider": "openai",
    "model": "openai/text-embedding-3-small",
    "apiKey": "YOUR_EDEN_AI_API_KEY",
    "apiBase": "https://api.edenai.run/v3"
  }
}

Step 3: Save and Reload

Save the configuration file
Reload your IDE or click “Reload” in Continue

Available Models

You can add any model from Eden AI’s catalog:

Chat Models

{
  "models": [
    {
      "title": "Claude 3.5 Sonnet",
      "provider": "openai",
      "model": "anthropic/claude-sonnet-4-5",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3"
    },
    {
      "title": "Claude 3 Opus",
      "provider": "openai",
      "model": "anthropic/claude-opus-4-5",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3"
    },
    {
      "title": "GPT-4 Turbo",
      "provider": "openai",
      "model": "openai/gpt-4-turbo",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3"
    },
    {
      "title": "Gemini 2.5 Pro",
      "provider": "openai",
      "model": "google/gemini-2.5-pro",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3"
    },
    {
      "title": "Command R+",
      "provider": "openai",
      "model": "cohere/command-r-plus",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3"
    }
  ]
}

Features

Chat

Open the Continue sidebar and start chatting with AI:

Select your model from the dropdown
Type your question or request
Get instant responses

Example prompts:

“Explain this code”
“Add error handling to this function”
“Write tests for this component”

Inline Editing

Select code and use Continue to edit it:

Highlight code
Press Cmd+I (Mac) / Ctrl+I (Windows/Linux)
Describe your changes
Review and accept

Example edits:

“Add type hints”
“Refactor this to use async/await”
“Simplify this logic”

Tab Autocomplete

Continue provides intelligent code completion:

Start typing
Continue suggests completions
Press Tab to accept

Configure fast models for autocomplete:

{
  "tabAutocompleteModel": {
    "title": "Fast Autocomplete",
    "provider": "openai",
    "model": "openai/gpt-3.5-turbo",
    "apiKey": "YOUR_EDEN_AI_API_KEY",
    "apiBase": "https://api.edenai.run/v3"
  }
}

Slash Commands

Use slash commands for common tasks:

/edit - Edit selected code
/comment - Add comments
/test - Generate tests
/fix - Fix errors
/explain - Explain code

Advanced Configuration

Custom Context Providers

Add codebase context for better responses:

{
  "models": [...],
  "contextProviders": [
    {
      "name": "code",
      "params": {}
    },
    {
      "name": "docs",
      "params": {
        "startUrl": "https://docs.edenai.co"
      }
    },
    {
      "name": "folder",
      "params": {
        "folder": "src"
      }
    }
  ]
}

Model-Specific Settings

Configure temperature and other parameters per model:

{
  "models": [
    {
      "title": "Claude 3.5 Sonnet (Creative)",
      "provider": "openai",
      "model": "anthropic/claude-sonnet-4-5",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3",
      "completionOptions": {
        "temperature": 0.9,
        "maxTokens": 2000
      }
    },
    {
      "title": "Claude 3.5 Sonnet (Precise)",
      "provider": "openai",
      "model": "anthropic/claude-sonnet-4-5",
      "apiKey": "YOUR_EDEN_AI_API_KEY",
      "apiBase": "https://api.edenai.run/v3",
      "completionOptions": {
        "temperature": 0.1,
        "maxTokens": 1000
      }
    }
  ]
}

Environment Variables

Use environment variables for API keys:

{
  "models": [
    {
      "title": "Claude 3.5 Sonnet",
      "provider": "openai",
      "model": "anthropic/claude-sonnet-4-5",
      "apiKey": "${EDEN_AI_API_KEY}",
      "apiBase": "https://api.edenai.run/v3"
    }
  ]
}

export EDEN_AI_API_KEY="your_api_key_here"

Use Cases

Code Generation

Generate entire functions or classes:

Open Continue chat
Describe what you need: “Create a Python class for user authentication with login, logout, and token refresh methods”
Review and insert the generated code

Code Review

Get AI-powered code reviews:

Select code
Open Continue chat
Ask: “Review this code for security issues and performance improvements”

Documentation

Generate documentation automatically:

Select a function
Use /comment command
Continue adds comprehensive docstrings

Debugging

Get help with errors:

Copy error message
Open Continue chat
Ask: “How do I fix this error?” and paste the error

Refactoring

Modernize legacy code:

Select old code
Use /edit command
Ask: “Refactor this to use modern Python features”

Expert Models as Tools (MCP)

Eden AI also hosts an MCP server that exposes the expert model catalog (OCR, web search, speech, translation and more) as tools. Add the server to your assistant’s config.yaml:

mcpServers:
  - name: Eden AI
    type: streamable-http
    url: https://mcp.edenai.run/mcp
    requestOptions:
      headers:
        Authorization: Bearer YOUR_EDEN_AI_API_KEY

The tools become available in Agent mode. See the MCP server page for the full tool catalog and the conventions its tools share.

Troubleshooting

Models Not Appearing

If models don’t appear in the dropdown:

Check config.json syntax is valid (use a JSON validator)
Ensure apiBase is exactly: https://api.edenai.run/v3
Reload the IDE

Authentication Errors

If you see 401 errors:

Verify your Eden AI API key in config.json
Check there are no extra spaces in the API key
Test the API key manually:

curl -X POST https://api.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5",
    "messages": [{"role": "user", "content": "test"}],
    "stream": true
  }'

Slow Responses

If responses are slow:

Use faster models for autocomplete (gpt-3.5-turbo)
Reduce maxTokens in completion options
Check your internet connection

Context Issues

If Continue doesn’t understand your codebase:

Add relevant context providers
Include specific files using @file in chat
Use folder context for project-wide understanding

Keyboard Shortcuts

VS Code

Cmd/Ctrl + I - Inline edit
Cmd/Ctrl + Shift + L - Open Continue sidebar
Cmd/Ctrl + Shift + R - Re-run last command

JetBrains

Alt + Enter - Show Continue actions
Cmd/Ctrl + Shift + C - Open Continue chat

Best Practices

1. Choose the Right Model

Quick edits: Use openai/gpt-3.5-turbo for speed
Complex reasoning: Use anthropic/claude-sonnet-4-5
Autocomplete: Use openai/gpt-3.5-turbo for low latency

2. Provide Context

Add context to get better responses:

Tag files with @filename
Include error messages
Describe the broader goal

3. Iterate

Don’t expect perfect results immediately:

Review generated code
Ask for adjustments
Combine AI suggestions with your expertise

4. Use Slash Commands

Leverage built-in commands for common tasks:

/edit for modifications
/test for test generation
/fix for error resolution

Example Workflows

Building a New Feature

Chat: “Help me design a REST API endpoint for user registration”
Review the suggested structure
Use /edit to implement the endpoint
Use /test to generate unit tests
Use /comment to add documentation

Debugging

Copy the error traceback
Chat: “Explain this error and suggest a fix: [paste error]”
Review the explanation
Use /fix on the problematic code
Test the solution

Code Review

Select a function
Chat: “Review this for security, performance, and maintainability”
Review suggestions
Use /edit to apply improvements
Use /test to ensure nothing broke

Next Steps

Claude Code - Official Claude CLI

​Overview

​Installation

​VS Code

​JetBrains IDEs

​Configuration

​Step 1: Open Configuration

​Step 2: Configure Eden AI

​Step 3: Save and Reload

​Available Models

​Chat Models

​Features

​Chat

​Inline Editing

​Tab Autocomplete

​Slash Commands

​Advanced Configuration

​Custom Context Providers

​Model-Specific Settings

​Environment Variables

​Use Cases

​Code Generation

​Code Review

​Documentation

​Debugging

​Refactoring

​Expert Models as Tools (MCP)

​Troubleshooting

​Models Not Appearing

​Authentication Errors

​Slow Responses

​Context Issues

​Keyboard Shortcuts

​VS Code

​JetBrains

​Best Practices

​1. Choose the Right Model

​2. Provide Context

​3. Iterate

​4. Use Slash Commands

​Example Workflows

​Building a New Feature

​Debugging

​Code Review

​Next Steps

Overview

Installation

VS Code

JetBrains IDEs

Configuration

Step 1: Open Configuration

Step 2: Configure Eden AI

Step 3: Save and Reload

Available Models

Chat Models

Features

Chat

Inline Editing

Tab Autocomplete

Slash Commands

Advanced Configuration

Custom Context Providers

Model-Specific Settings

Environment Variables

Use Cases

Code Generation

Code Review

Documentation

Debugging

Refactoring

Expert Models as Tools (MCP)

Troubleshooting

Models Not Appearing

Authentication Errors

Slow Responses

Context Issues

Keyboard Shortcuts

VS Code

JetBrains

Best Practices

1. Choose the Right Model

2. Provide Context

3. Iterate

4. Use Slash Commands

Example Workflows

Building a New Feature

Debugging

Code Review

Next Steps