Skip to main content
Blackbox AI is a VS Code extension for AI-powered coding assistance. It supports custom OpenAI-compatible API providers, allowing you to connect to Infercom’s EU sovereign inference platform.
Setup time: ~2 minutes

​
Prerequisites

​
Configuration

​
Step 1: Open Blackbox Settings

  1. Open VS Code
  2. Click the Blackbox AI icon in the sidebar
  3. Click the Settings (gear icon) in the top-right of the Blackbox panel

​
Step 2: Configure API Provider

In the Settings dialog, enter:
FieldValue
API ProviderOpenAI Compatible
Base URLhttps://api.infercom.ai/v1
API KeyYour Infercom API key
Model IDMiniMax-M2.5

​
Step 3: Configure Model Settings

Expand MODEL CONFIGURATION and set:
FieldValue
Supports ImagesUnchecked
Context Window Size163840
Max Output Tokens-1 (unlimited)

​
Step 4: Save

Click Save to apply the configuration. Blackbox AI settings configured for Infercom

​
Model

Use MiniMax-M2.5 - optimized for agentic coding with 160K context and 75.8% SWE-bench.
MetricValue
SWE-bench75.8%
Context Window160K tokens
Throughput400+ tokens/sec
ReasoningBuilt-in

​
Verification

After setup, test with a simple prompt: 
Write a Python function to check if a number is prime
The response should show MiniMax-M2.5’s fast inference (typically under 300ms time-to-first-token).

​
Troubleshooting

​
”Invalid API Key” error

  • Verify your API key at cloud.infercom.ai
  • Ensure no extra spaces in the API key field

​
”Model not found” error

  • Check model ID is exactly MiniMax-M2.5 (case-sensitive)
  • Verify available models: curl https://api.infercom.ai/v1/models

​
Slow responses

  • Check your internet connection
  • Infercom API is hosted in EU (Munich) - latency may vary by location
  • First request may be slower due to model loading

​
Next Steps