Strengths
- Up to 1M-token context (512K guaranteed)
- Thinking between tool calls
- Text, image and video input
- Published weights
Best For
- Coding assistants
- Long agent tasks and workflow automation
- Long-video analysis
Run It in EDDI
The fastest route is the Manager: open the agent wizard or the Platform Operator and pick the provider and model. To configure it yourself, follow these steps for the provider you want.
MiniMax · type: "minimax"
Model ids: MiniMax-M3, MiniMax-M2.7
1. Store the credential
Add the provider's API key to the Secrets Vault in the Manager, or with PUT /secretstore/secrets/default/minimax-key, under the name used below. Configurations reference it as ${vault:…}, so the key never appears in plain text.
${vault:minimax-key}2. Configure the LLM task
Use this as the langchain.json of the agent's workflow, or paste the parameters into the LLM editor in the Manager.
{
"tasks": [
{
"actions": [
"send_message"
],
"id": "chat",
"type": "minimax",
"parameters": {
"apiKey": "${vault:minimax-key}",
"modelName": "MiniMax-M3",
"systemMessage": "You are a helpful assistant",
"addToOutput": "true"
}
}
]
}Or create the whole agent in one call
setup_agent writes the rules, LLM configuration and workflow, then deploys the agent. Call it over MCP or POST /administration/agents/setup.
setup_agent(
agentName: "My MiniMax-M3 agent",
systemPrompt: "You are a helpful assistant.",
provider: "minimax",
model: "MiniMax-M3",
apiKey: "${vault:minimax-key}"
)Notes for EDDI
- This provider requires the model's reasoning to be sent back during tool loops. EDDI's preset does it for you: leave
returnThinkingandsendThinkingat their defaults. - EDDI never sends a JSON response format to MiniMax. When you need JSON, set
convertToObjectand describe the shape in the prompt.
Related Models
Sources
The facts on this page come from the vendor's documentation, checked on 2026-09-30. Models change quickly, so confirm limits with the vendor before you rely on them. Prices are not listed here: see the vendor's pricing page.