Compared to traditional translation, using AI as a translation channel has significant advantages. OpenAI ChatGPT, Gemini, and Claude excel in translation quality, but they require a VPN and payment with a foreign credit card, which poses higher barriers to entry and is not user-friendly for domestic users.
Fortunately, domestic AI technology is also developing rapidly. The API interfaces of these domestic AI services are fully compatible with the OpenAI SDK, which means you can seamlessly replace OpenAI without modifying any code. Examples include Deepseek, Alibaba BaiLian, Zhipu AI, Baichuan Intelligent, Silicon Flow, etc.
You only need to fill in the API URL, SK (API Key), and Model Name these 3 key pieces of information into the software's Menu -- Translation Settings -- OpenAI ChatGPT API, and you can immediately start using it.
No complex configuration is required, even beginners can easily get started!
Deepseek
This is Deepseek's official API service, but it has been unstable recently.
Official website: https://www.deepseek.com
API KEY(SK) acquisition address: https://platform.deepseek.com/api_keys
API URL: https://api.deepseek.com/v1
Available models: deepseek-chat (i.e. v3 model), deepseek-reasoner (i.e. R1 reasoning model)
Zhipu AI
Official website: https://bigmodel.cn
API KEY(SK) acquisition address: https://bigmodel.cn/usercenter/proj-mgmt/apikeys
API URL: https://open.bigmodel.cn/api/paas/v4
Available models: glm-4-plus, glm-4-air, glm-4-air-0111, glm-4-airx, glm-4-long, glm-4-flashx, glm-4-flash
Note: glm-4-flash is a free model that requires no cost. Other models are paid and require a balance in the account.
Baichuan Intelligent
Official website: https://www.baichuan-ai.com
API KEY(SK) acquisition address: https://platform.baichuan-ai.com/console/apikey
API URL: https://api.baichuan-ai.com/v1
Available models: Baichuan4-Turbo, Baichuan4-Air, Baichuan4, Baichuan3-Turbo, Baichuan3-Turbo-128k, Baichuan2-Turbo
Moonshot AI Kimi
Official website: https://www.moonshot.cn
API KEY(SK) acquisition address: https://platform.moonshot.cn/console/api-keys
API URL: https://api.moonshot.cn/v1
Available models: moonshot-v1-8k, moonshot-v1-32k, moonshot-v1-128k
Lingyi Wanwu
Official website: https://lingyiwanwu.com
API KEY acquisition address: https://platform.lingyiwanwu.com/apikeys
API URL: https://api.lingyiwanwu.com/v1
Available models: yi-lightning
Alibaba BaiLian
Alibaba BaiLian is an AI model marketplace that provides all Alibaba series models and other manufacturers' models, including Deepseek-r1.
Official website: https://bailian.console.aliyun.com
API KEY(SK) acquisition address: https://bailian.console.aliyun.com/?apiKey=1#/api-key
API URL: https://dashscope.aliyuncs.com/compatible-mode/v1
Available models: Many, see details at https://bailian.console.aliyun.com/#/model-market
Silicon Flow
Another AI marketplace similar to Alibaba BaiLian, providing mainstream domestic models, including deepseek-r1
Official website: https://siliconflow.cn
API KEY(SK) acquisition address: https://cloud.siliconflow.cn/account/ak
API URL: https://api.siliconflow.cn/v1
Available models: Many, see details at https://cloud.siliconflow.cn/models?types=chat
Note: Silicon Flow provides the Qwen/Qwen2.5-7B-Instruct free model, which can be used directly without any cost.
ByteDance Volcano Engine Ark
An AI marketplace similar to Alibaba BaiLian, in addition to gathering the Doubao series models, there are also some third-party models, including deepseek-r1.
Official website: https://www.volcengine.com/product/ark
API KEY(SK) acquisition address: https://console.volcengine.com/ark/region:ark+cn-beijing/apiKey
API URL: https://ark.cn-beijing.volces.com/api/v3
MODELS: Many, see details at https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW
Note: ByteDance Volcano Engine Ark's compatibility with the OpenAI SDK is a bit strange. You cannot directly fill in the model name. You need to create an inference endpoint in the Volcano Engine console in advance, select the model to use in the inference endpoint, and then fill in the inference endpoint ID to the place where the model is needed, that is, in the software. If you find it troublesome, you can ignore it. Besides the slightly lower price, it has no other advantages. See how to create an inference endpoint: https://www.volcengine.com/docs/82379/1099522
Other compatible OpenAI API usage methods
This article only lists some AI usage methods. Other services that are compatible with the OpenAI API can be used in a similar way, as long as the API interface address, SK, and model name are determined.
Note that the API URL generally ends with /v1.