Interface GlobalDefaultProvider

Provider identifier (e.g. "openai", "anthropic", "openrouter", "ollama").

Default text model for this provider (e.g. "gpt-4o-mini"), used by generateText, streamText and agents. Embedding and image calls use it too unless it is recognizably a chat model (GPT, Claude, Gemini, Llama, MiniMax and similar families) sent to the provider's own endpoint, in which case the provider's default model for the task applies. With a custom endpoint, and for embedText on Ollama, it is always used. The endpoint is the base URL the call is sent to: the call's own baseUrl, else baseUrl here, else the provider's base-URL env var, each read as resolveBaseUrl in model.ts reads it: an empty or whitespace-only one is unset and the next source applies, and with none the call goes to the provider's own endpoint. OpenAI's API root https://api.openai.com/v1 and the regional roots OpenAI's data residency guide names (https://us.api.openai.com/v1, https://eu.api.openai.com/v1 and the au, ca, jp, in, sg, kr, gb and ae ones), and MiniMax's API roots, https://api.minimax.io/v1, the China root https://api.minimax.cn/v1 that MiniMax's China documentation names and the older China root https://api.minimaxi.com/v1, are the provider's own endpoint, not a custom one, whether the call, this default or the base-URL env var gives them, compared as fetch sends the URL: the letter case of the scheme and the host, a default port, surrounding whitespace and trailing slashes make no difference.

API key used when no inline override is supplied.

Base URL override (useful for proxies, local Ollama, etc.). An empty or whitespace-only value is unset: the provider's base-URL env var applies, and with none text and image calls go to the provider's own endpoint (Ollama and stable-diffusion-local, which have none, refuse them with no request).