Contents
Terminology
| Terminology | Description |
|---|---|
| Token | The text generation model processes text in Token-based units. Token represents a common sequence of characters. For example, a single Chinese character“Kui” might be decomposed into a combination of tokens, while a short and common phrase like“China” might use a single Token. Roughly speaking, one Token is equivalent to about 1.5-2 Chinese characters for a typical Chinese text. |
| QPS | Queries Per Second |
| RPM | Requests Per Minute |
| TPM | Tokens Per Minute |
| TPD | Tokens Per Day |
APIs
Limit QPS only
- CogniHub - I am CogniHub API to provide developers with large model reasoning API registered developer accounts, you can get APPKEY can switch all major large language models on the market, compatible with the OpenAI API
Easily blocked IP, Limit models
- gpt4free - The official gpt4free repository | various collection of powerful language models
Limit QPS/times/models
- GPT_API_free - Free CHATGPT API Key, Free CHATGPT API, support GPT4 API (Free) , CHATGPT domestic available Free forwarding API, direct connect without proxy. Can be used with ChatBox and other software/plug-ins, greatly reduce the cost of using the interface. Domestic can be unlimited free chat.
Limit total times/tokens/RPM/PRD
- Coze - Coze is a next-generation AI application and chatbot development platform. Regardless of your programming experience, Coze enables you to effortlessly create various chatbots and deploy them across different social platforms and messaging apps.
Limit total times
- LLaMA3.1-8B - NVIDIA LLaMA3.1-8B is a large language model that can be used for a variety of natural language processing tasks, including text generation, translation, and question answering. It is based on the LLaMA architecture and is trained on a large dataset of text from the internet.
Limit total times/validity
- DeepSeek - The DeepSeek API uses an OpenAI-compatible API format, and by modifying the configuration, you can use the OpenAI SDK to access the DeepSeek API, or use OpenAI API-compatible software.
Limit models/concurrence/RPM/TPM/TPD
- Kimi - Moonshot provides HTTP-based API service access, and for most apis, we are compatible with the OpenAI SDK.
Limit models/total Tokens
- ChatGLM - BigModel. AI MaaS Platform. Call GLM model APIs easily. Build AI applications quickly.
Limit QPS/models
- Spark Lite - Spark Large Model API: · Overall capability close to GPT 4-Turbo, voice large model leading the way · Suitable for various business scenarios, but also provides large model life cycle customization tools · Lite version access free, pro/MAX/Ultra version industry low price
Limit models/total Tokens/validity
- Spark 4.0 Ulta and etc - Spark Large Model API: the most powerful spark large model version, the effect is excellent, all-round improvement effect, leading the peak of intelligence, optimization of Internet search links, provide accurate answers, strengthen the ability of text summary, enhance office productivity