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:
Architecture: Mixture of Experts (MoE)
Customer API alias:
gonka-autoModel 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.