delorex/test-repo
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: upgrade MiniMax model references from M2.5 to M2.7

Browse Source 
Update all documentation to reference the latest MiniMax-M2.7 and
MiniMax-M2.7-highspeed models, replacing the previous M2.5 series.
Also updates the CLI backend section with the current API endpoint
(api.minimax.io) and platform URL.

Co-Authored-By: Octopus <liyuan851277048@icloud.com>
This commit is contained in:
Octopus
2026-03-18 07:57:16 -05:00
committed by PR Bot
parent fc096759fb
commit 7ce6f4fd40
5 changed files with 17 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/en/stage-1/1.1-introduction-to-ai-ide/index.md
+1 -1
View File
@@ -624,7 +624,7 @@ You can do this:
|------|-----------------| |------|-----------------|
| Doubao-Seed Series | ✅ Supported | | Doubao-Seed Series | ✅ Supported |
| GLM-4.7 / 4.6 | ❌ Not Supported | | GLM-4.7 / 4.6 | ❌ Not Supported |
| MiniMax-M2.1 / M2 | ❌ Not Supported | | MiniMax-M2.7 / M2.5 | ❌ Not Supported |
| DeepSeek-V3.1 | ❌ Not Supported | | DeepSeek-V3.1 | ❌ Not Supported |
| Kimi-K2.5 | ✅ Supported | | Kimi-K2.5 | ✅ Supported |
| Kimi-K2-0905 | ❌ Not Supported | | Kimi-K2-0905 | ❌ Not Supported |
docs/en/stage-1/1.3-integrating-ai-capabilities/index.md
+7 -7
View File
@@ -169,16 +169,16 @@ In addition to DeepSeek, you can also try other large language models. Since mos
::: details Learn More: What is MiniMax? ::: details Learn More: What is MiniMax?
**MiniMax** is a Chinese AI company dedicated to general artificial intelligence research. MiniMax has developed its own MiniMax-M2.5 series of large language models, which perform well in multiple benchmarks with excellent cost-effectiveness. **MiniMax** is a Chinese AI company dedicated to general artificial intelligence research. MiniMax has developed its own MiniMax-M2.7 series of large language models, which perform well in multiple benchmarks with excellent cost-effectiveness.
**Key Features of MiniMax-M2.5 Series:** **Key Features of MiniMax-M2.7 Series:**
- **Ultra-long context**: Supports a 204,800-token context window, suitable for processing long documents and multi-turn conversations - **Ultra-long context**: Supports a 204,800-token context window, suitable for processing long documents and multi-turn conversations
- **Cost-effective**: Input $0.3/M tokens, Output $1.2/M tokens, extremely competitive pricing - **Cost-effective**: Extremely competitive pricing
- **OpenAI-compatible API**: Can be called directly using the OpenAI SDK, no need to learn a new API format - **OpenAI-compatible API**: Can be called directly using the OpenAI SDK, no need to learn a new API format
- **Two available models**: - **Two available models**:
- `MiniMax-M2.5`: Flagship model for complex tasks - `MiniMax-M2.7`: Flagship model for complex tasks
- `MiniMax-M2.5-highspeed`: High-speed version with same performance but faster response - `MiniMax-M2.7-highspeed`: High-speed version with same performance but faster response
::: :::
The integration process is the same as DeepSeek, just three steps: The integration process is the same as DeepSeek, just three steps:
@@ -194,7 +194,7 @@ curl https://api.minimax.io/v1/chat/completions \
-H "Content-Type: application/json" \ -H "Content-Type: application/json" \
-H "Authorization: Bearer ${MINIMAX_API_KEY}" \ -H "Authorization: Bearer ${MINIMAX_API_KEY}" \
-d '{ -d '{
"model": "MiniMax-M2.5", "model": "MiniMax-M2.7",
"messages": [ "messages": [
{"role": "system", "content": "You are a helpful assistant."}, {"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"} {"role": "user", "content": "Hello!"}
@@ -207,7 +207,7 @@ curl https://api.minimax.io/v1/chat/completions \
MiniMax's API format is almost identical to DeepSeek (both are OpenAI-compatible), so if you've already successfully integrated DeepSeek, switching to MiniMax only requires changing three things: MiniMax's API format is almost identical to DeepSeek (both are OpenAI-compatible), so if you've already successfully integrated DeepSeek, switching to MiniMax only requires changing three things:
1. **Base URL**: Change to `https://api.minimax.io/v1` 1. **Base URL**: Change to `https://api.minimax.io/v1`
2. **API Key**: Use your MiniMax API Key 2. **API Key**: Use your MiniMax API Key
3. **Model name**: Change to `MiniMax-M2.5` or `MiniMax-M2.5-highspeed` 3. **Model name**: Change to `MiniMax-M2.7` or `MiniMax-M2.7-highspeed`
For more details, refer to the [MiniMax OpenAI Compatible API Documentation](https://platform.minimax.io/docs/api-reference/text-openai-api). For more details, refer to the [MiniMax OpenAI Compatible API Documentation](https://platform.minimax.io/docs/api-reference/text-openai-api).
::: :::
docs/zh-cn/appendix/8-artificial-intelligence/ai-capability-dictionary.md
+1 -1
View File
@@ -49,7 +49,7 @@
> - OpenAI 系列：GPT-4、GPT-4.1、GPT-4o、GPT-5.1 等 > - OpenAI 系列：GPT-4、GPT-4.1、GPT-4o、GPT-5.1 等
> - Google 系列：Gemini 1.5 Pro、Gemini 1.5 Flash 等 > - Google 系列：Gemini 1.5 Pro、Gemini 1.5 Flash 等
> - Anthropic 系列：Claude 3.5 Sonnet、Claude 3.5 Haiku 等 > - Anthropic 系列：Claude 3.5 Sonnet、Claude 3.5 Haiku 等
> - 国内模型：通义千问 Qwen 系列、文心一言 ERNIE Bot 系列、GLM/智谱清言、腾讯混元、讯飞星火、月之暗面的 Kimi 背后的大模型、MiniMax MiniMax-M2.5 系列等 > - 国内模型：通义千问 Qwen 系列、文心一言 ERNIE Bot 系列、GLM/智谱清言、腾讯混元、讯飞星火、月之暗面的 Kimi 背后的大模型、MiniMax MiniMax-M2.7 系列等
> >
> 更偏视觉和视频方向的大模型和服务，包括： > 更偏视觉和视频方向的大模型和服务，包括：
> >
docs/zh-cn/stage-1/1.1-introduction-to-ai-ide/index.md
+1 -1
View File
@@ -631,7 +631,7 @@ AI 会根据你的描述，直接修改 React 组件和样式。保存后刷新
|------|-----------------| |------|-----------------|
| Doubao-Seed 系列 | ✅ 支持 | | Doubao-Seed 系列 | ✅ 支持 |
| GLM-4.7 / 4.6 | ❌ 不支持 | | GLM-4.7 / 4.6 | ❌ 不支持 |
| MiniMax-M2.1 / M2 | ❌ 不支持 | | MiniMax-M2.7 / M2.5 | ❌ 不支持 |
| DeepSeek-V3.1 | ❌ 不支持 | | DeepSeek-V3.1 | ❌ 不支持 |
| Kimi-K2.5 | ✅ 支持 | | Kimi-K2.5 | ✅ 支持 |
| Kimi-K2-0905 | ❌ 不支持 | | Kimi-K2-0905 | ❌ 不支持 |
docs/zh-cn/stage-1/1.3-integrating-ai-capabilities/index.md
+7 -7
View File
@@ -173,16 +173,16 @@ curl \
::: details 了解更多：MiniMax 是什么？ ::: details 了解更多：MiniMax 是什么？
**MiniMax** 是一家中国人工智能公司，致力于通用人工智能技术的研发。MiniMax 推出了自研的 MiniMax-M2.5 大语言模型系列，在多项基准测试中表现优异，具有极高的性价比。 **MiniMax** 是一家中国人工智能公司，致力于通用人工智能技术的研发。MiniMax 推出了自研的 MiniMax-M2.7 大语言模型系列，在多项基准测试中表现优异，具有极高的性价比。
**MiniMax-M2.5 系列的主要特点：** **MiniMax-M2.7 系列的主要特点：**
- **超长上下文**：支持 204,800 tokens 的上下文窗口，适合处理长文档、多轮对话 - **超长上下文**：支持 204,800 tokens 的上下文窗口，适合处理长文档、多轮对话
- **高性价比**：输入 $0.3/M tokens，输出 $1.2/M tokens，价格极具竞争力 - **高性价比**：价格极具竞争力
- **OpenAI 兼容接口**：可以直接使用 OpenAI SDK 调用，无需额外学习新的 API 格式 - **OpenAI 兼容接口**：可以直接使用 OpenAI SDK 调用，无需额外学习新的 API 格式
- **两个可用模型**： - **两个可用模型**：
- `MiniMax-M2.5`：旗舰模型，适合复杂任务 - `MiniMax-M2.7`：旗舰模型，适合复杂任务
- `MiniMax-M2.5-highspeed`：高速版本，保持同样的性能但更快 - `MiniMax-M2.7-highspeed`：高速版本，保持同样的性能但更快
::: :::
接入方式与 DeepSeek 一致，只需要三步： 接入方式与 DeepSeek 一致，只需要三步：
@@ -198,7 +198,7 @@ curl https://api.minimax.io/v1/chat/completions \
-H "Content-Type: application/json" \ -H "Content-Type: application/json" \
-H "Authorization: Bearer ${MINIMAX_API_KEY}" \ -H "Authorization: Bearer ${MINIMAX_API_KEY}" \
-d '{ -d '{
"model": "MiniMax-M2.5", "model": "MiniMax-M2.7",
"messages": [ "messages": [
{"role": "system", "content": "You are a helpful assistant."}, {"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"} {"role": "user", "content": "Hello!"}
@@ -211,7 +211,7 @@ curl https://api.minimax.io/v1/chat/completions \
MiniMax 的 API 格式与 DeepSeek 几乎完全一致（都是 OpenAI 兼容格式），所以如果你已经成功接入了 DeepSeek，切换到 MiniMax 只需要修改三个地方： MiniMax 的 API 格式与 DeepSeek 几乎完全一致（都是 OpenAI 兼容格式），所以如果你已经成功接入了 DeepSeek，切换到 MiniMax 只需要修改三个地方：
1. **基础 URL**：改为 `https://api.minimax.io/v1` 1. **基础 URL**：改为 `https://api.minimax.io/v1`
2. **API Key**：使用 MiniMax 的 API Key 2. **API Key**：使用 MiniMax 的 API Key
3. **模型名称**：改为 `MiniMax-M2.5` 或 `MiniMax-M2.5-highspeed` 3. **模型名称**：改为 `MiniMax-M2.7` 或 `MiniMax-M2.7-highspeed`
更多信息请参考 [MiniMax OpenAI 兼容接口文档](https://platform.minimax.io/docs/api-reference/text-openai-api)。 更多信息请参考 [MiniMax OpenAI 兼容接口文档](https://platform.minimax.io/docs/api-reference/text-openai-api)。
::: :::