LLM API

Yeap Cloud LLM API is a model gateway that follows the OpenAI API format. Activate the service in the console, create an API key, and you can call chat, embedding, image and speech models from several providers through one endpoint and one authentication scheme. You pay for what you use.

#Key capabilities

• OpenAI-compatible API: the base URL is https://llm.yeap.cloud/v1 and requests authenticate with Authorization: Bearer sk-.... Code that already uses an OpenAI SDK usually only needs a new base_url and key.
• Many models: the console page LLM API → Models & pricing lists the available models and their prices. You can also query GET /v1/models.
• Per-key controls: each key can have its own quota cap, model allowlist, IP allowlist and expiry time.
• Usage visibility: Usage logs records the model, token counts and cost of every call. Usage statistics summarises usage over a time range.
• Browser testing: the Playground lets you try chat, image generation and text-to-speech without writing code.

#In this section

• Quickstart: activate the service, add quota, create a key and send your first request with curl, Python or Node.js.
• API keys, quota and usage: key settings, how key quota relates to your balance, and logs and statistics.
• Playground: try models in the browser.