Use MiniMax M3 with Kilo Code — velqa.dev
Kilo Code is an OpenAI-compatible VS Code coding agent. Configure it in a few fields to use velqa.dev; checkout is Stripe, in USD, by international card.
Prerequisites
- VS Code with the Kilo Code extension installed
- A velqa.dev API key (see the quickstart)
Configuration
- Open Kilo Code in the VS Code sidebar
- Select Bring my own Key if this is your first setup
- Under API Provider, choose OpenAI Compatible
- Fill in the fields:
| Field | Value |
|---|---|
| Base URL | https://api.velqa.dev/v1 |
| API Key | sk-... |
| Model ID | minimax-m3 |
| Context Window Size | 131072 |
| Max Output Tokens | 16384 |
- Click Save
Context window and output (important)
Fill in Context Window Size and Max Output Tokens in the OpenAI Compatible provider's advanced settings. They tell Kilo Code when to compact the context. Without them, a long agentic session lets the context grow unbounded and eventually triggers Trop de tokens demandes. Reessaie plus tard., while burning through your quota faster.
Values per model:
| Model ID | Context Window Size | Max Output Tokens |
|---|---|---|
minimax-m3 | 131072 | 16384 |
hy3 | 262144 | 16384 |
glm-4.7-flash | 200000 | 16384 |
deepseek-v4-flash | 65536 | 8192 |
Recommended models
| Model ID | Use case |
|---|---|
minimax-m3 | Code generation, completion |
glm-4.7-flash | Chat, quick questions — the most responsive |
deepseek-v4-flash | High-volume, economical |
Pricing
Velqa.dev credits are bought in USD through Stripe, by international card. See velqa.dev/models for the current model catalogue.
Troubleshooting
- `Invalid API Key`: re-copy the key from the velqa.dev dashboard (it is only shown at creation)
- `Model Not Found`: the model identifier must match exactly those listed at velqa.dev/models
- Empty response: check that your velqa.dev balance is positive