Continue.dev

Route Continue.dev traffic through Axemere Gateway in about 2 minutes. Continue is built for custom endpoints: a single apiBase line per model in your config is all that's needed.

Prerequisites

• Continue.dev installed in VS Code or JetBrains: Quickstart
• A gateway key: created in Console → Gateway Keys
• A workload ID: from Console → Workloads

How It Works

Continue.dev routes each model's requests to the apiBase specified in config.yaml. Point that URL at Axemere Gateway and every Continue request, including inline completions, chat, and slash commands, flows through the gateway's policy engine before reaching the AI provider.

Privacy: Axemere never stores, logs, or accesses the content of AI prompts or responses. Only request metadata (model, token counts, latency, attribution) is recorded. See Execution Records for exactly what is and isn't kept.

Setup

Global configuration

Edit ~/.continue/config.yaml:

models:
  - name: Claude via Axemere
    provider: anthropic
    model: claude-sonnet-4-6
    apiBase: https://us.gw.axemere.ai/proxy/anthropic/k/mvgc_k_your-key-here/w/your-workload
    apiKey: unused
  - name: GPT-4o via Axemere
    provider: openai
    model: gpt-4o
    apiBase: https://us.gw.axemere.ai/proxy/openai/k/mvgc_k_your-key-here/w/your-workload/v1
    apiKey: unused

Replace:

• mvgc_k_your-key-here with your gateway key from Gateway Keys
• your-workload with your workload ID from Workloads

The apiKey field is required by Continue but ignored by the gateway; authentication uses the key embedded in the URL.

Tip — Project attribution: Add /p/my-project after the workload segment to tag requests by project for per-repo spend tracking:

https://us.gw.axemere.ai/proxy/anthropic/k/mvgc_k_your-key-here/w/continue/p/my-project

See Proxy Path Attribution for the full URL schema.

Per-project configuration

Create .continue/config.yaml in your project root to override the global config for that project. This lets you set a project-specific attribution segment per repo while sharing the same gateway key globally.

Verify Traffic Is Flowing

1. Reload VS Code or restart your JetBrains IDE after saving config.yaml.
2. Open the Continue chat panel and send any message.
3. Check Records in the Axemere console; the request should appear within a few seconds, attributed to your workload.

Next Steps