# AhoosAI documentation AhoosAI develops the Nimbus language models and provides them through three products: an online studio, an offline studio for your own computer, and a public API compatible with OpenAI's Chat Completions format. This documentation describes what you need to use them. ## Sections {#sections} - [API reference](api.html): the endpoint, authentication, request and response formats, streaming, tools and errors. - [API rules and limits](rules.html): usage limits, API keys, acceptable use and data handling. - [Models](models.html): the models that are available and what they accept. - [Studio](studio.html): the online studio and the offline studio. ## One account {#account} All online services share one sign-in at [ahoos-ai.site/services](https://ahoos-ai.site/services/). Signing in gives you access to the online studio, to the platform where API keys are created, and to your usage figures. The offline studio needs no account. ## Quick start {#quick-start} 1. Sign in at [ahoos-ai.site/services](https://ahoos-ai.site/services/). 2. Open the [platform](https://ahoos-ai.site/services/platforme/) and create an API key. The key is shown only once; store it securely. 3. Send a request: ```bash curl https://ahoos-ai.site/services/api/v1/chat/completions \ -H "Authorization: Bearer nim_YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "nimbus-2-apex", "messages": [{"role": "user", "content": "Hello"}]}' ``` The first request after a period without traffic can take up to two minutes while the model starts. Later requests begin immediately. ## For AI tools {#ai-tools} Every page of this documentation is also published as plain Markdown text: replace `.html` with `.en.txt` or `.fa.txt` in the address (for example [api.en.txt](api.en.txt)). An index of the site for language models is available at [/llms.txt](https://ahoos-ai.site/llms.txt). ## Contact {#contact} Questions and reports: [Support@ahoos-ai.site](mailto:Support@ahoos-ai.site) or the [contact form](https://ahoos-ai.site/contact/).