Models / MiniMax M2.7

MiniMax M2.7 on Gonka

Technical specifications and API capabilities of the MiniMax M2.7 model used by the Gonka decentralized AI network.

Network model: MiniMax M2.7
Architecture: Mixture of Experts (MoE)
Customer API alias: gonka-auto

Model scale

  • 228.7 billion total parameters
  • 256 experts with eight experts selected per token
  • 62 transformer layers
  • 204,800-token native context window
  • FP8 open-weight checkpoint

What it is designed for

MiniMax M2.7 is designed for coding, tool use, multi-step reasoning, and complex agent workflows. Its sparse MoE architecture activates only a small subset of experts for each token.

Gonka deployment

MiniMax M2.7 is an approved Gonka network model. Gonka Broker uses it through the verified decentralized route without exposing infrastructure-provider details.

API access

Use the OpenAI-compatible POST /v1/chat/completions endpoint with the customer alias gonka-auto. Route selection remains managed by Gonka Broker.


Next step: Create an account or read the integration docs.