VS Code has no built-in Dahl provider. Use a coding extension that supports an OpenAI-compatible API, for example Cline, Roo Code, Kilo Code or Continue. Each needs the same three things: the base URL with /v1, a key with tokens on it, and a model ID.
Get a key with tokens
In /account → API keys, Allocate tokens from the pool to a key (a new key starts at 0), then copy the key.
Cline, Roo Code, Kilo Code
Open the extension settings and pick the OpenAI Compatible provider:
API Provider: OpenAI Compatible Base URL: https://inference.dahl.global/v1 API Key: dahl_… Model ID: MiniMaxAI/MiniMax-M2.7
If the extension asks for the context window, use the value from Models: 180K for MiniMax M2.7, 400K for DeepSeek V4 Flash and GLM 5.3 Flash. Turn image input off — current models do not accept images. For agent work start with MiniMaxAI/MiniMax-M2.7.
Continue
Add the model to ~/.continue/config.yaml:
name: My Config
version: 0.0.1
schema: v1
models:
- name: MiniMax M2.7 (Dahl)
provider: openai
model: MiniMaxAI/MiniMax-M2.7
apiBase: https://inference.dahl.global/v1
apiKey: dahl_…provider: openai means the OpenAI API format; apiBase points it at Dahl.
Prefer the terminal? OpenCode runs in the VS Code terminal too.
Common errors
| Message | Cause | Fix |
|---|---|---|
available tokens exhausted (402) | The key has 0 tokens | Allocate from the pool in /account |
Method Not Allowed (405) | Base URL without /v1 | Use https://inference.dahl.global/v1 |
This model is not currently offered (400) | Wrong or stale model ID | Use an exact id from GET /v1/models |
This model is at concurrency capacity (429) | The model is full at peak hours | Retry after Retry-After or switch model. See Errors |