MiniMax M3.1 Flash

Description

MiniMax M3.1 Flash is MiniMax's open-weight native multimodal mixture-of-experts model (about 428B total, 23B active parameters) for coding, agentic workflows, computer use and cybersecurity. It takes text, image and video input with a 1M-token context window, and adds sparse attention throughout, quantization-aware training and DSpark speculative decoding on top of MiniMax M3. Reasoning is always on, with tunable effort.

Providers

Tensorix

View provider details and policies.

Quantization: Unknown

Capabilities

EU-Compliant API Access

Use MiniMax M3.1 Flash with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

curl https://api.eurouter.info/api/v1/chat/completions \
  -H "Authorization: Bearer $EUROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3.1-flash",
    "messages": [{"role": "user", "content": "Hello"}]
  }'