MiniMax

MiniMax M2.5

Token Plan MiniMax model for text generation and reasoning.

MiniMaxChatReasoningneeds review

Visual demos

Example media slots

MiniMax

Prompt demo

Coding assistant

Draft a TypeScript adapter for an Alibaba Model Studio compatible chat completion endpoint.

Reasoning demo

Enterprise summary

Summarize the business case for Alibaba Token Plan Team Edition in five bullets.

Routing demo

Model routing

Choose the best Qwen model for a low-latency catalog search assistant with cost controls.

These are safe placeholder slots. Swap in official Alibaba-provided logos, posters, and demo videos when asset usage is approved.

Inputs

System PromptUser Prompt

Advanced settings

TemperatureTop PMax TokensStreamingJSON ModeDemo token

Cost

Unknown

Pricing has not been verified. Treat this model as needs_review for production use.

Unpriced usageNeeds review

Output

text

No run output yet.

License

Provider terms Commercial status: unknown.

Deployment

Available through Token Plan Team Edition. Execution requires a Token Plan-specific key/base URL adapter.

Limits

Limits need admin review.

API Examples

curl -X POST https://nfero.com/api/models/MiniMax-M2.5/run \
  -H 'content-type: application/json' \
  -d '{"system_prompt":"You are a precise, helpful assistant.","prompt":"Explain why Singapore-region inference matters for a public AI demo.","temperature":0.7,"top_p":0.8,"max_tokens":512,"stream":false,"json_mode":false}'

await fetch('/api/models/MiniMax-M2.5/run', {
  method: 'POST',
  headers: { 'content-type': 'application/json' },
  body: JSON.stringify({
  "system_prompt": "You are a precise, helpful assistant.",
  "prompt": "Explain why Singapore-region inference matters for a public AI demo.",
  "temperature": 0.7,
  "top_p": 0.8,
  "max_tokens": 512,
  "stream": false,
  "json_mode": false
})
});

import requests
requests.post('https://nfero.com/api/models/MiniMax-M2.5/run', json={
  "system_prompt": "You are a precise, helpful assistant.",
  "prompt": "Explain why Singapore-region inference matters for a public AI demo.",
  "temperature": 0.7,
  "top_p": 0.8,
  "max_tokens": 512,
  "stream": false,
  "json_mode": false
})

Recent Runs

No runs recorded yet.