Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

tian-minghui/openai-style-api

支持将openai、claude、azure openai, gemini,kimi, 智谱AI,通义千问,讯飞星火API等模型服务方的调用转为openai方式调用。屏蔽不同大模型API的差异，统一用openai api标准格式使用大模型(Shield the differences between different large model APIs and use large models in a unified openai API standard format)

43MITPython

View on GitHub

Stars: 420
Forks: 65
Watchers: 8
Open issues: 20
Contributors: 5

Star history, last 90 days+3 over 16 snapshots

2026-08-04 · 4172026-11-04 · 420

Star history, last 90 days
Date	Stars
2026-08-04	417
2026-08-11	418
2026-08-12	418
2026-08-18	418
2026-08-19	418
2026-08-30	418
2026-09-14	417
2026-09-16	418
2026-09-25	417
2026-10-01	417
2026-10-02	417
2026-10-08	417
2026-10-20	418
2026-10-21	419
2026-11-02	420
2026-11-04	420

Today

— stars today

This week

+1 stars this week

This month

+3 stars this month

Momentum

0.0

growth rate 0.24%/day

From the README


# openai-style-api


 ***本人精力有限，某些模型更新可能无法及时更新，如果遇到问题请提issue，也欢迎有兴趣的大佬提PR***

## 用途
屏蔽不同大模型API的差异，统一用openai api标准格式使用大模型, 也可以用来做api-key的二次分发管理; 配置化管理不同大模型调用参数，让你在使用大模型的时候只需关注 api-key 和 messages

## 功能

- [x] 支持多种大模型，当前已支持
  - [x] openai
  - [x] azure open ai
  - [x] claude-api 【api申请在等待列表，暂未测试】
  - [x] claude-web (将web端功能封装成openai api)
  - [x] 智谱ai
  - [x] kimi
  - [x] bingchat(copilot)
  - [ ] 百度文心一言
  - [x] 讯飞星火
  - [x] gemini
  - [x] 通义千问
  - [ ] ...
- [x] 支持stream方式调用
- [x] 支持open ai的第三方代理服务，比如openai-sb等
- [x] 支持在线更新配置 `http://0.0.0.0:8090/`（这个前端页面和交互完全是用gpt写的 哈哈）
- [x] 支持负载均衡，一个key可轮训/随机/并行等访问多个模型
- [x] 支持按照model_name进行路由

**更新日志**

2024-04-03
- 支持通义千问
- 优化异常处理


## 部署方式

**项目的核心配置依赖model-config.json文件，若是没有model-config.json，默认会使用model-config-default.json启动，这时虽然能启动起来，但是因为api-key等没有配置，无法调用成功。**

### Docker

本地新建一个model-config.json文件，根据下边配置文件示例，进行配置， 然后运行以下命令

    docker pull tianminghui/openai-style-api

    docker run -d -p 8090:8090 --name openai-style-api\
    -e ADMIN-TOKEN=admin \
    -v /path/to/your/model-config.json:/app/model-config.json \
    tianminghui/openai-style-api

`/path/to/your/model-config.json` 替换成你自己的本地路径

### Docker compose
clone本项目，或者下载项目中的`docker-compose.yml`文件，修改其中的`./model-config.json`路径, 然后运行以下命令

    docker-compose up -d


### 本地部署
1. `git clone https://github.com/tian-minghui/openai-style-api.git` 拉取项目代码
2. `cp model-config-default.json model-config.json`  并按需修改配置文件model-config.json
3.  `pip install -r  requirements.txt` 
4. 运行 `python open-api.py`


## 配置说明
model-config.json 配置文件简单示例

```
    [
        {
            "token": "f2b7295fc440db7f",
            "type": "azure",  // azure openai 模型
            "config": {
                "api_base": "https://xxxx.openai.azure.com/",
                "deployment_id": "gpt-35-turbo",
                "api_version": "2023-05-15",
                "api_key": "xxxxxx",
                "temperature": 0.8
            }
        }
    ]
```
- 整个文件是一个json list，可以配置多个模型，只要token不重复就行
- token 自定义的token，后续在请求的时候拿着这个token来请求
- type 类型，表示以下config中的配置是那个模型的，比如 openai，通义千问
- config， 配置openai的api_base, api_key, model等， 针对不用模型有不同的配置（下边有配置示例，更详细配置可以看代码）， 此处的配置优先于客户端请求中的配置，比如"temperature": 0.8,  会覆盖请求中的temperature（这里的想法是可以针对同一个模型，调整不同参数，映射成一个新模型）

## 使用方式

### curl

    curl http://localhost:8090/v1/chat/completions \
          -H "Content-Type: application/json" \
          -H "Authorization: Bearer f2b7295fc440db7f" \
          -d '{
            "messages": [
              {
                "role": "system",
                "content": "You are a helpful assistant."
              },
              {
                "role": "user",
                "content": "Hello!"
              }
            ]
          }'

### openai库调用

openai<1.0.0 使用如下方式

    import openai

    openai.api_key = "f2b7295fc440db7f"
    openai.api_base = "http://localhost:8090/v1"

    completion = openai.ChatCompletion.create(
        model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}])
    print(completion.choices[0].message.content)


openai>=1.0.0使用以下方式调用
    
    import os
    from openai import OpenAI

    client = OpenAI(
        # This is the default and can be omitted
        api_key='kimi-GxqT3BlbkFJj',
        base_url = 'http://localhost:8090/v1'
    )

    chat_completion = client.chat.completions.create(
        messages=[
            {
                "role": "user",
                "content": "Say this is a test",
            }
        ],
        model="gpt-3.5-turbo",
    )

    print(chat_completion.choices[0].message.content)

### 第三方应用

[ChatGPT Next Web](https://github.com/Yidadaa/ChatGPT-Next-Web)
![Alt text](img/image.png)

## 配置示例
    [
    {
        "token": "f2b7295fc440db7f",
        "type": "azure",  // azure openai 模型
        "config": {
            "api_base": "https://xxxx.openai.azure.com/",
            "deployment_id": "gpt-35-turbo",
            "api_version": "2023-05-15",
            "api_key": "xxxxxx",
            "temperature": 0.8

Excerpt of 7,281 characters

Read on GitHub

Top contributors

No contributor data yet — it is fetched during the contributor sync pass.

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

43/10043

Maintenance: 5%; How recently the default branch was pushed to
Releases: 10%; Recency and cadence of tagged releases
Community: 41%; Contributor breadth and bus factor
Issue backlog: 60%; Open issues measured against the size of the audience
Documentation: 81%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No commits in over a year
No release in over a year
Usable in commercial products with attribution.

Details

Created: 3 years ago
Last push: 3 years ago
Last release: 3 years ago
Release tag: v0.1
Releases in the last year: 0
Default branch: main
Size: 301 KB
Owner type: User
Owner location: 北京
Discovered via: phrase:openai api
First indexed: 3 months ago
Last synced: 3 days ago

tian-minghui/openai-style-api

43MITPython

View on GitHub

Stars: 420
Forks: 65
Watchers: 8
Open issues: 20
Contributors: 5

Star history, last 90 days+3 over 16 snapshots

2026-08-04 · 4172026-11-04 · 420

Star history, last 90 days
Date	Stars
2026-08-04	417
2026-08-11	418
2026-08-12	418
2026-08-18	418
2026-08-19	418
2026-08-30	418
2026-09-14	417
2026-09-16	418
2026-09-25	417
2026-10-01	417
2026-10-02	417
2026-10-08	417
2026-10-20	418
2026-10-21	419
2026-11-02	420
2026-11-04	420

Today

— stars today

This week

+1 stars this week

This month

+3 stars this month

Momentum

0.0

growth rate 0.24%/day

From the README


# openai-style-api


 ***本人精力有限，某些模型更新可能无法及时更新，如果遇到问题请提issue，也欢迎有兴趣的大佬提PR***

## 用途
屏蔽不同大模型API的差异，统一用openai api标准格式使用大模型, 也可以用来做api-key的二次分发管理; 配置化管理不同大模型调用参数，让你在使用大模型的时候只需关注 api-key 和 messages

## 功能

- [x] 支持多种大模型，当前已支持
  - [x] openai
  - [x] azure open ai
  - [x] claude-api 【api申请在等待列表，暂未测试】
  - [x] claude-web (将web端功能封装成openai api)
  - [x] 智谱ai
  - [x] kimi
  - [x] bingchat(copilot)
  - [ ] 百度文心一言
  - [x] 讯飞星火
  - [x] gemini
  - [x] 通义千问
  - [ ] ...
- [x] 支持stream方式调用
- [x] 支持open ai的第三方代理服务，比如openai-sb等
- [x] 支持在线更新配置 `http://0.0.0.0:8090/`（这个前端页面和交互完全是用gpt写的 哈哈）
- [x] 支持负载均衡，一个key可轮训/随机/并行等访问多个模型
- [x] 支持按照model_name进行路由

**更新日志**

2024-04-03
- 支持通义千问
- 优化异常处理


## 部署方式

**项目的核心配置依赖model-config.json文件，若是没有model-config.json，默认会使用model-config-default.json启动，这时虽然能启动起来，但是因为api-key等没有配置，无法调用成功。**

### Docker

本地新建一个model-config.json文件，根据下边配置文件示例，进行配置， 然后运行以下命令

    docker pull tianminghui/openai-style-api

    docker run -d -p 8090:8090 --name openai-style-api\
    -e ADMIN-TOKEN=admin \
    -v /path/to/your/model-config.json:/app/model-config.json \
    tianminghui/openai-style-api

`/path/to/your/model-config.json` 替换成你自己的本地路径

### Docker compose
clone本项目，或者下载项目中的`docker-compose.yml`文件，修改其中的`./model-config.json`路径, 然后运行以下命令

    docker-compose up -d


### 本地部署
1. `git clone https://github.com/tian-minghui/openai-style-api.git` 拉取项目代码
2. `cp model-config-default.json model-config.json`  并按需修改配置文件model-config.json
3.  `pip install -r  requirements.txt` 
4. 运行 `python open-api.py`


## 配置说明
model-config.json 配置文件简单示例

```
    [
        {
            "token": "f2b7295fc440db7f",
            "type": "azure",  // azure openai 模型
            "config": {
                "api_base": "https://xxxx.openai.azure.com/",
                "deployment_id": "gpt-35-turbo",
                "api_version": "2023-05-15",
                "api_key": "xxxxxx",
                "temperature": 0.8
            }
        }
    ]
```
- 整个文件是一个json list，可以配置多个模型，只要token不重复就行
- token 自定义的token，后续在请求的时候拿着这个token来请求
- type 类型，表示以下config中的配置是那个模型的，比如 openai，通义千问
- config， 配置openai的api_base, api_key, model等， 针对不用模型有不同的配置（下边有配置示例，更详细配置可以看代码）， 此处的配置优先于客户端请求中的配置，比如"temperature": 0.8,  会覆盖请求中的temperature（这里的想法是可以针对同一个模型，调整不同参数，映射成一个新模型）

## 使用方式

### curl

    curl http://localhost:8090/v1/chat/completions \
          -H "Content-Type: application/json" \
          -H "Authorization: Bearer f2b7295fc440db7f" \
          -d '{
            "messages": [
              {
                "role": "system",
                "content": "You are a helpful assistant."
              },
              {
                "role": "user",
                "content": "Hello!"
              }
            ]
          }'

### openai库调用

openai<1.0.0 使用如下方式

    import openai

    openai.api_key = "f2b7295fc440db7f"
    openai.api_base = "http://localhost:8090/v1"

    completion = openai.ChatCompletion.create(
        model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}])
    print(completion.choices[0].message.content)


openai>=1.0.0使用以下方式调用
    
    import os
    from openai import OpenAI

    client = OpenAI(
        # This is the default and can be omitted
        api_key='kimi-GxqT3BlbkFJj',
        base_url = 'http://localhost:8090/v1'
    )

    chat_completion = client.chat.completions.create(
        messages=[
            {
                "role": "user",
                "content": "Say this is a test",
            }
        ],
        model="gpt-3.5-turbo",
    )

    print(chat_completion.choices[0].message.content)

### 第三方应用

[ChatGPT Next Web](https://github.com/Yidadaa/ChatGPT-Next-Web)
![Alt text](img/image.png)

## 配置示例
    [
    {
        "token": "f2b7295fc440db7f",
        "type": "azure",  // azure openai 模型
        "config": {
            "api_base": "https://xxxx.openai.azure.com/",
            "deployment_id": "gpt-35-turbo",
            "api_version": "2023-05-15",
            "api_key": "xxxxxx",
            "temperature": 0.8

Excerpt of 7,281 characters

Read on GitHub

Top contributors

No contributor data yet — it is fetched during the contributor sync pass.

Quality score

Would you bet a product on this? Bounded 0–100 and slow moving.

43/10043

Maintenance: 5%; How recently the default branch was pushed to
Releases: 10%; Recency and cadence of tagged releases
Community: 41%; Contributor breadth and bus factor
Issue backlog: 60%; Open issues measured against the size of the audience
Documentation: 81%; README depth, plus a homepage and topics
Licensing: 100%; How freely the code can be adopted

What to know before adopting

No commits in over a year
No release in over a year
Usable in commercial products with attribution.

Details

Created: 3 years ago
Last push: 3 years ago
Last release: 3 years ago
Release tag: v0.1
Releases in the last year: 0
Default branch: main
Size: 301 KB
Owner type: User
Owner location: 北京
Discovered via: phrase:openai api
First indexed: 3 months ago
Last synced: 3 days ago

Top AI Repos — open-source AI, indexed and scored

tian-minghui/openai-style-api

From the README

Top contributors

Quality score

What to know before adopting

Categories

Details

tian-minghui/openai-style-api

From the README

Top contributors

Quality score

What to know before adopting

Categories

Details

Top AI Repos — open-source AI, indexed and scored

Trend

From the README

Top contributors

Quality score

What to know before adopting

Categories

Details

Trend

From the README

Top contributors

Quality score

What to know before adopting

Categories

Details