Continue Integration

AVELIN API is compatible with Continue — an open-source AI code assistant for VS Code and JetBrains. Continue provides inline completions, chat, and code editing powered by any OpenAI-compatible API.

Continue is the open-source alternative to GitHub Copilot and Cursor, living natively inside VS Code and JetBrains IDEs. Its killer feature is @codebase context: Continue indexes your entire repository for semantic search, then sends the most relevant code snippets to the model automatically. When you ask "how does authentication work?", it finds the auth middleware, the login handler, and the session store — without you manually copying files. Combined with tab autocomplete, chat (Ctrl+L), and inline edit (Ctrl+I), Continue gives you a full AI coding workflow inside the IDE you already use, with no vendor lock-in and your choice of model provider.

Why AVELIN + Continue? Open-source, self-hostable, and IDE-native — paired with AVELIN's 1M-token context models and competitive per-token pricing.


Quick Setup

Step 1: Get your AVELIN API key

Sign up at avelin.ai and generate an API key. It will look like sk-ave...xxxx.

Step 2: Install Continue

  • VS Code: Search "Continue" in Extensions and install
  • JetBrains: Install from JetBrains Marketplace

Step 3: Configure Continue

Open Continue's config.json (click the gear icon in the Continue panel) and add AVELIN:

{
  "models": [
    {
      "title": "AVELIN Coding Plus",
      "provider": "openai",
      "model": "avelin-coding-pro",
      "apiBase": "https://api.avelin.ai/v1",
      "apiKey": "sk-a..."
    },
    {
      "title": "AVELIN Pro",
      "provider": "openai",
      "model": "avelin-pro",
      "apiBase": "https://api.avelin.ai/v1",
      "apiKey": "sk-a..."
    },
    {
      "title": "AVELIN Fast",
      "provider": "openai",
      "model": "avelin-fast",
      "apiBase": "https://api.avelin.ai/v1",
      "apiKey": "sk-a..."
    }
  ],
  "tabAutocompleteModel": {
    "title": "AVELIN Fast Autocomplete",
    "provider": "openai",
    "model": "avelin-fast",
    "apiBase": "https://api.avelin.ai/v1",
    "apiKey": "sk-a..."
  }
}

Step 4: Start Coding

  1. Select your AVELIN model from the Continue dropdown
  2. Use Ctrl+L (chat) or Ctrl+I (inline edit) to start

For Chat & Edit: avelin-coding-pro

Featureavelin-coding-proWhy it matters for Continue
Context window1M tokensFull codebase awareness
Max output65K tokensLarge file generation
Throughput~100 tokens/secFast inline edits

For Autocomplete: avelin-fast

Featureavelin-fastWhy it matters for Continue
LatencyLowInstant tab completions
CostLowest tierEconomical for high-volume autocomplete

All Models

Use caseModel
Chat & inline editavelin-coding-pro
Architecture reviewavelin-coding-ultra
Quick questionsavelin-fast
General reasoningavelin-pro

Why AVELIN for Continue?

  • Open-source + open API: Both Continue and AVELIN's API surface are open — no vendor lock-in
  • Prompt caching: ~80% cost reduction on repeated system prompts and codebase context
  • 1M context: Continue's @codebase feature works best with large context windows
  • Fast autocomplete: avelin-fast provides low-latency tab completions

Advanced Configuration

Configure embeddings for better @codebase results:

{
  "embeddingsProvider": {
    "provider": "openai",
    "model": "bge-m3",
    "apiBase": "https://api.avelin.ai/v1",
    "apiKey": "sk-a..."
  }
}

Custom Slash Commands

{
  "customSlashCommands": [
    {
      "name": "review",
      "description": "Review code for security and performance issues",
      "prompt": "Review this code for security vulnerabilities, performance issues, and best practices."
    }
  ]
}

Troubleshooting

IssueSolution
"Model not found"Check model name matches exactly
Autocomplete too slowUse avelin-fast for tab completion model
Context errorsReduce context size or switch to avelin-coding-pro (1M)
Connection failedVerify apiBase is https://api.avelin.ai/v1