1. MiniMax
toiotech
  • toiotech接口说明
  • 已支持的模型列表
  • 大模型官方文档
  • Claude thinking 多轮对话
  • thinking相关说明
  • 已支持的模型列表
    • 语言大模型
      • OpenAI
        • gpt-4
        • gpt-4.1
        • gpt-4o
        • gpt-4o-mini
        • gpt-5
        • gpt-5-chat
        • gpt-5-mini
        • gpt-5-nano
        • gpt-5.1
        • gpt-5.1-chat-latest
        • gpt-5.1-codex(仅支持/v1/responses)
        • gpt-5.2
        • gpt-5.2(responses)
        • gpt-5.2-chat
        • gpt-5.2-pro(仅支持/v1/responses)
        • gpt-oss-120b
        • o1
        • o3
        • o3-mini
        • o3-deep-research
        • o3-pro
        • o4-mini
        • o4-mini-deep-research
        • gpt-5.4
        • gpt-5.4-pro
      • Google
        • gemini-2.0-flash
        • gemini-2.5-computer-use-preview-10-2025
        • gemini-2.5-flash
        • gemini-2.5-flash-lite
        • gemini-2.5-flash-lite-preview
        • gemini-2.5-pro
        • gemini-3-flash-preview
        • gemini-3-pro-preview
        • gemini-robotics-er-1.5-preview
        • gemini-(thinking_config)openai请求格式
        • gemini-3.1-pro-preview(多模态)
        • gemini-3.1-flash-lite-preview(多模态)
        • gemini-3.1-flash-lite-preview(thinking)
        • gemini-2.5-pro(原生请求格式)
      • Anthropic
        • 通用接口
        • claude-opus-4-5-20251101
        • claude-opus-4-20250514
        • claude-sonnet-4-20250514
        • claude-sonnet-4-5-20250929
        • claude-(Interleaved thinking)
        • claude-opus-4-6
        • claude-sonnet-4-6
      • DeepSeek
        • deepseek-chat
        • deepseek-reasoner
      • MiniMax
        • abab6.5s-chat
          POST
        • minimax-m2
          POST
        • minimax-m2.5
          POST
      • Moonshot
        • kimi-k2
        • kimi-k2-0711-preview
        • kimi-k2-0905
        • kimi-k2-instruct
        • kimi-k2-thinking
        • moonshot-v1-128k
        • moonshot-v1-32k
        • moonshot-v1-8k
        • moonshot-v1-128k-vision-preview
        • moonshot-v1-32k-vision-preview
        • moonshot-v1-8k-vision-preview
        • kimi-k2.5
        • 获取系统工具
        • 执行系统工具
      • xAI
        • grok-4
        • grok-4-1-fast-non-reasoning
        • grok-4-1-fast-reasoning
      • 字节跳动
        • 通用接口
        • doubao-1.8图片理解
        • doubao-1.8(视频理解)
        • doubao-seed-2-0-pro-260215(图片理解)
        • doubao-seed-2-0-pro-260215(视频理解)
      • 智谱
        • glm-4-plus
        • glm-4.5
        • glm-4.6
        • glm-4.7
        • glm-5
      • 阿里巴巴
        • qwen-max
        • qwen-max-2025-01-25
        • qwen-max-latest
        • qwen-plus
        • qwen-plus-latest
        • qwen-turbo
        • qwen2.5-7b-instruct
        • qwen2.5-32b-instruct
        • qwen2.5-72b-instruct
        • qwen3-coder-plus
        • qwen3-coder-plus-2025-07-22
        • qwen3-max
        • qwen3-max-preview
        • qwen3-235b-a22b
        • qwen3-235b-a22b-instruct-2507
        • qwen3-235b-a22b-thinking-2507
        • qwen3-8b
        • qwen3-coder-30b-a3b-instruct
        • qwen3-next-80b-a3b-instruct
        • qwen3-next-80b-a3b-thinking
        • qwen-vl-max(视觉理解)
        • qwen-vl-plus(视觉理解)
        • qwen3-vl-235b-a22b-instruct(视觉理解)
        • qwen3-vl-235b-a22b-thinking(视觉理解)
        • qwen3-vl-30b-a3b-thinking(图片理解)
        • qwen3-vl-30b-a3b-thinking(视频理解)
        • qwen3-max-2026-01-23(qwen3-max-thinking)
        • qwen3-max-2026-01-23(非思考模式)
        • qwen3.5-397b-a17b(多模态)
        • qwen3.5-plus(多模态)
        • qwen3.5-flash(多模态)
        • qwen3.5-122b-a10b(多模态)
        • qwen3.5-35b-a3b
        • qwen3.5-omni-plus(视频+文本)
        • qwen3.5-omni-plus(音频+文本)
        • qwen3.5-omni-plus(图片+文本)
        • qwen3.5-omni-flash(图片+文本)
      • 百度
        • ernie-x1-32k
        • ernie-5.0-thinking-exp
        • ernie-5.0-thinking-preview
      • 腾讯
        • hunyuan-t1-latest
      • 讯飞
        • SparkDesk-v4.0
      • 蚂蚁
        • Ling-1T
        • Ring-1T
      • 阶跃星辰
        • step-3
      • 小米
        • mimo-v2-pro
        • mimo-v2-omni(多模态理解)
    • 图片生成
      • 通用接口
        • 图片生成
        • 图片编辑
      • OpenAI
        • gpt-image系列图片生成
        • gpt-image系列图片编辑
        • dall-e-3图片生成
      • Google
        • gemini-3-pro-image-preview
        • gemini-3.1-flash-image-preview
        • gemini-2.5-flash-image
        • gemini-2.5-flash-image-preview
      • Anthropic
      • BFL
        • flux-1-kontext-pro
      • ImagineArt
        • imagineart-1.5-preview
      • 字节跳动豆包
        • doubao-seedream-5-0-260128(文生图)
        • doubao-seedream-5-0-260128(图生图)
    • 音视频处理
      • OpenAI
        • gpt-4o-audio-preview
        • gpt-audio
      • 阿里巴巴
        • qwen3-tts-flash
      • Elevenlabs
        • eleven_v3
      • MiniMax
        • 通用接口
    • 视频生成
      • Vidu
        • vidu-2.0-img2video
        • viduq2-pro提交图生视频任务
        • viduq3-pro图生视频
        • viduq3-pro文生视频
      • 字节跳动
        • 提交图生视频生成任务
        • 提交文生视频生成任务
      • 快手
        • kling提交图生视频任务
        • kling提交文生视频任务
        • kling-v3提交图生视频任务
        • kling-v3提交文生视频任务
      • 腾讯
        • hunyuan-video-v1.5
      • 海螺
        • 提交图生视频任务
        • 提交文生视频任务
      • sora
        • sora-2
        • sora-2-pro
      • Google
        • veo-3.1-generate-preview
        • veo-3.1-fast-generate-preview
      • 阿里巴巴
        • wan2.6-i2v
        • wan2.6-t2v
      • pixverse
        • pixverse-v5.5-t2v
        • pixverse-v5.5-i2v
        • pixverse-v5.6-i2v
        • pixverse-v5.6-t2v
      • ltx
        • 文生视频
        • 图生视频
      • worldlabs
        • 文生视频(world)
        • 图生视频(world)
        • 多图生视频(world)
      • runawayml
        • 提交gen4.5(文生视频)
        • 提交gen4.5(图生视频)
    • 多模态模型
      • 智谱
        • glm-4.5v
        • glm-4.6v
      • 阿里巴巴
        • qwen2.5-omni-7b
        • qwen2.5-vl-72b-instruct
        • qwen3-omni-flash-2025-12-01
      • 日日新
        • SenseNova-V6-Pro
    • Realtime
      • OpenAI
        • gpt-4o-mini-realtime-preview
        • gpt-4o-realtime-preview
        • gpt-realtime-1.5
      • qwen阿里云
        • qwen3-omni-flash-realtime
      • gemini
        • gemini-3.1-flash-live-preview
    • 向量化
      • OpenAI
        • text-embedding-3-large
        • text-embedding-3-small
        • text-embedding-ada-002
        • text-embedding-v1
    • 代码解释器
      • qwen3-模型
  • 已支持的搜索服务
    • serper
      • get方式
      • post方式
  • gemini
    • openai格式
      • gpt-5.2
      • openai格式
      • gemini-开启thinking
    • google原生格式
      • gemini-robotics-er-1.5-preview
      • google格式
  • anthropic
    • anthropic格式
      • anthropic格式
      • tools调用
      • thinking
      • image理解
      • code_execution
      • 关闭thinking
    • openai格式
      • openai格式
  • openai
    • chat/completions
    • 流式/chat/completions
    • responses
  • deepseek
    • chat/completions
  • qwen
    • qwen提交文生视频任务
    • qwen提交图生视频任务
    • qwen3-omni-flash
    • chat/completions(开启thinking)
    • chat/completions
  • 获取异步任务结果
    GET
  1. MiniMax

minimax-m2.5

POST
/v1/chat/completions

Input:Text#

Output:Text#

官方文档

Request

Authorization
Provide your bearer token in the
Authorization
header when making requests to protected resources.
Example:
Authorization: Bearer ********************
Body Params application/jsonRequired

Example
{
    "model": "minimax-m2",
    "messages": [
        {
            "content": "You are a helpful assistant",
            "role": "system"
        },
        {
            "content": "Hi",
            "role": "user"
        }
    ],
    "max_tokens": 4096,
    "stream": false,
    "temperature": 1
}

Request Code Samples

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
curl --location --request POST 'https://api.toiotech.com/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "minimax-m2",
    "messages": [
        {
            "content": "You are a helpful assistant",
            "role": "system"
        },
        {
            "content": "Hi",
            "role": "user"
        }
    ],
    "max_tokens": 4096,
    "stream": false,
    "temperature": 1
}'

Responses

🟢200OK
application/json
Body

Example
{
    "id": "019b681a731ae556e91034b0d09d632e",
    "object": "chat.completion",
    "created": 1766978122,
    "model": "MiniMaxAI/MiniMax-M2",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\nHello! 🌟 I'm happy to help — just tell me what you're thinking or where I can assist today.😊",
                "reasoning_content": "Hmm, the user just said \"Hi\" - it's a simple greeting. \n\nFirst, I should prioritize warmth and openness since this is the start of an interaction. The \"🌟\" emoji adds friendly energy without overdoing it. \n\nThe response works two ways: it acknowledges their greeting while gently signaling I'm here for more. The \"how can I help?\" question keeps it patient - they might just be testing the waters.\n\nI notice the user didn't include any topic or request. That's okay! Leaving space for them to lead feels right. The tone should stay approachable but not pressure them to share anything. \n\n...Wondering if they're new to AI assistants? Maybe. Keeping the tone reassuring and open is wise either way. No assumptions.\n"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 22,
        "completion_tokens": 174,
        "total_tokens": 196,
        "completion_tokens_details": {
            "reasoning_tokens": 150
        },
        "prompt_tokens_details": {
            "cached_tokens": 0
        },
        "prompt_cache_hit_tokens": 0,
        "prompt_cache_miss_tokens": 22
    },
    "system_fingerprint": ""
}
Modified at 2026-02-25 11:08:30
Previous
minimax-m2
Next
kimi-k2
Built with