MiniMax M2.5

by minimax · family minimax-m

Facts

Release date	2026-02-12
Retired date	—
Knowledge cutoff	—
Context (max)	204,800
Max output	—
Modalities	text → text
Aliases	`MiniMax-M2.5`
Open weights	yes (MiniMax-AI/MiniMax-M2.5)
Description	Thinking cannot be turned off; thinking.type disabled has no effect.

Unknown values are shown as —.

Offerings

Provider	Wire ID	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
IO Intelligence (io.net)	`MiniMaxAI/MiniMax-M2.5`	chat	openai-chat	ga	0.35 / 1.37	effort · default on · mandatory · returns reasoning_content
MiniMax	`MiniMax-M2.5`	chat-completions	openai-chat	ga	0.30 / 1.20	always_on · default on · mandatory · returns reasoning_content · round-trips reasoning_content
MiniMax Token Plan	`MiniMax-M2.5`	anthropic	anthropic-messages	ga	—	always_on · default on · mandatory · returns reasoning_content · round-trips reasoning_content
OpenCode Go	`minimax-m2.5`	go-messages	anthropic-messages	ga	—	always_on · default on · mandatory · returns reasoning_content · round-trips reasoning_content
OpenCode Zen	`minimax-m2.5`	chat-completions	openai-chat	ga	0.30 / 1.20	always_on · default on · mandatory · returns reasoning_content · round-trips reasoning_content
OpenRouter	`minimax/minimax-m2.5`	chat-completions	openai-chat	ga	0.23 / 0.90	effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

Reasoning controls

IO Intelligence (io.net)· MiniMaxAI/MiniMax-M2.5· chat effort

reasoning.effort lowmediumhigh● Default not documented — verify.

effort · default on · mandatory · returns reasoning_content

MiniMax· MiniMax-M2.5· chat-completions always_on

always_on · default on · mandatory · returns reasoning_content · round-trips reasoning_content

MiniMax Token Plan· MiniMax-M2.5· anthropic always_on

always_on · default on · mandatory · returns reasoning_content · round-trips reasoning_content

OpenCode Go· minimax-m2.5· go-messages always_on

always_on · default on · mandatory · returns reasoning_content · round-trips reasoning_content

OpenCode Zen· minimax-m2.5· chat-completions always_on

always_on · default on · mandatory · returns reasoning_content · round-trips reasoning_content

OpenRouter· minimax/minimax-m2.5· chat-completions effort

reasoning.effort lowmedium●highxhighmax

effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

Example requests

IO Intelligence (io.net) · openai-chat · MiniMaxAI/MiniMax-M2.5

curl 'https://api.intelligence.io.solutions/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "MiniMaxAI/MiniMax-M2.5",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "high"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.intelligence.io.solutions/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "MiniMaxAI/MiniMax-M2.5",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "high"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.intelligence.io.solutions/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "MiniMaxAI/MiniMax-M2.5",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "high"
    }
  }),
})
console.log(await resp.json())

MiniMax · openai-chat · MiniMax-M2.5

curl 'https://api.minimax.io/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "MiniMax-M2.5",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ]
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.minimax.io/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "MiniMax-M2.5",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ]
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.minimax.io/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "MiniMax-M2.5",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ]
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

MiniMax Token Plan · anthropic-messages · MiniMax-M2.5

curl 'https://api.minimax.io/anthropic' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "MiniMax-M2.5",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ]
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.minimax.io/anthropic",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "MiniMax-M2.5",
      "max_tokens": 1024,
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ]
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.minimax.io/anthropic", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "MiniMax-M2.5",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ]
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenCode Go · anthropic-messages · minimax-m2.5

curl 'https://opencode.ai/zen/go/v1/messages' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "minimax-m2.5",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ]
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/go/v1/messages",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "minimax-m2.5",
      "max_tokens": 1024,
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ]
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/go/v1/messages", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "minimax-m2.5",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ]
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenCode Zen · openai-chat · minimax-m2.5

curl 'https://opencode.ai/zen/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "minimax-m2.5",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ]
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "minimax-m2.5",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ]
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "minimax-m2.5",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ]
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenRouter · openai-chat · minimax/minimax-m2.5

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "minimax/minimax-m2.5",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "medium"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "minimax/minimax-m2.5",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "medium"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "minimax/minimax-m2.5",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "medium"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).