Editors — Dahl Docs

VS Code, Continue, and Cline all call the same OpenAI-compatible API. Base URL `https://inference.dahl.global/v1`, Bearer key, model IDs from `GET /v1/models`. The snippets below can go stale when the network rotates models — refresh the id strings from that list.

VS Code

VS Code 1.122+. Chat BYOK does not need a GitHub Copilot plan. Inline completions still do.
Open the chat model picker → Manage Language Models, or Command Palette → Chat: Manage Language Models.
Add Models → Custom Endpoint. API type: Chat Completions — not Responses, not Messages.
Paste the JSON. Save. Pick MiniMax M2.7. If the models do not appear, restart VS Code.
Older VS Code without Custom Endpoint: use Continue instead.

[
  {
    "name": "Dahl",
    "vendor": "customendpoint",
    "apiType": "chat-completions",
    "apiKey": "${input:dahlApiKey}",
    "models": [
      {
        "id": "MiniMaxAI/MiniMax-M2.7",
        "name": "MiniMax M2.7",
        "url": "https://inference.dahl.global/v1/chat/completions",
        "toolCalling": true,
        "vision": false,
        "maxInputTokens": 200000,
        "maxOutputTokens": 8192
      },
      {
        "id": "deepseek-ai/DeepSeek-V4-Flash-0731",
        "name": "DeepSeek V4 Flash",
        "url": "https://inference.dahl.global/v1/chat/completions",
        "toolCalling": true,
        "vision": false,
        "maxInputTokens": 1000000,
        "maxOutputTokens": 8192
      }
    ]
  }
]

Continue

Same chat completions. apiBase is https://inference.dahl.global/v1 — do not append /chat/completions. Store the key as Continue secret DAHL_API_KEY.

name: Dahl
version: 1.0.0
schema: v1
models:
  - name: MiniMax M2.7
    provider: openai
    model: MiniMaxAI/MiniMax-M2.7
    apiBase: https://inference.dahl.global/v1
    apiKey: ${{ secrets.DAHL_API_KEY }}
  - name: DeepSeek V4 Flash
    provider: openai
    model: deepseek-ai/DeepSeek-V4-Flash-0731
    apiBase: https://inference.dahl.global/v1
    apiKey: ${{ secrets.DAHL_API_KEY }}

Cline

API Provider: OpenAI Compatible
Base URL: https://inference.dahl.global/v1
API Key: your Dahl Bearer key
Model: exact id from `GET /v1/models` — start with MiniMaxAI/MiniMax-M2.7

Codex

Codex CLI uses Responses, not chat completions. Config is on the API page.