The route mdask() takes and the address, key and model of each
route (your own OpenAI-compatible server, each provider such as Anthropic or
OpenAI, a local or LAN Ollama server), shared with rmoriebricklayer
and the packages built on it. A thin front to
rmoriebricklayer::llmcfg(), which saves them in
~/.config/morie/llm.json only when you pass a setting; from the
shell, rmbl config and rmbl config setup do the same.
Examples
if ("llmcfg" %in% getNamespaceExports("rmoriebricklayer")) {
mdllmconf() # reading writes nothing
}
#> key value source env
#> 1 route auto default MORIE_LLM_ROUTE
#> 2 own.url (not set) default MORIE_LLM_BASE_URL
#> 3 own.key (not set) default MORIE_LLM_API_KEY
#> 4 own.model (not set) default MORIE_LLM_MODEL
#> 5 ollama.url http://localhost:11434 default OLLAMA_HOST
#> 6 ollama.model (the first one pulled) default OLLAMA_MODEL
#> 7 ollama.key (not set) default OLLAMA_API_KEY
#> 8 openai.key (not set) default OPENAI_API_KEY
#> 9 openai.model (not chosen) default MORIE_OPENAI_MODEL
#> 10 anthropic.key (not set) default ANTHROPIC_API_KEY
#> 11 anthropic.model claude-opus-5-5 default MORIE_ANTHROPIC_MODEL
#> 12 gemini.key (not set) default GEMINI_API_KEY
#> 13 gemini.model (not chosen) default MORIE_GEMINI_MODEL
#> 14 openrouter.key (not set) default OPENROUTER_API_KEY
#> 15 openrouter.model (not chosen) default MORIE_OPENROUTER_MODEL
#> 16 groq.key (not set) default GROQ_API_KEY
#> 17 groq.model (not chosen) default MORIE_GROQ_MODEL
#> 18 together.key (not set) default TOGETHER_API_KEY
#> 19 together.model (not chosen) default MORIE_TOGETHER_MODEL
#> 20 fireworks.key (not set) default FIREWORKS_API_KEY
#> 21 fireworks.model (not chosen) default MORIE_FIREWORKS_MODEL
#> 22 deepseek.key (not set) default DEEPSEEK_API_KEY
#> 23 deepseek.model (not chosen) default MORIE_DEEPSEEK_MODEL
#> 24 mistral.key (not set) default MISTRAL_API_KEY
#> 25 mistral.model (not chosen) default MORIE_MISTRAL_MODEL
#> 26 xai.key (not set) default XAI_API_KEY
#> 27 xai.model (not chosen) default MORIE_XAI_MODEL
#> 28 cerebras.key (not set) default CEREBRAS_API_KEY
#> 29 cerebras.model (not chosen) default MORIE_CEREBRAS_MODEL
#> 30 perplexity.key (not set) default PERPLEXITY_API_KEY
#> 31 perplexity.model sonar-pro default MORIE_PERPLEXITY_MODEL
#> 32 huggingface.key (not set) default HF_TOKEN
#> 33 huggingface.model (not chosen) default MORIE_HUGGINGFACE_MODEL
#> 34 opencode.key (not set) default OPENCODE_API_KEY
#> 35 opencode.model (not chosen) default MORIE_OPENCODE_MODEL
#> 36 cohere.key (not set) default COHERE_API_KEY
#> 37 cohere.model (not chosen) default MORIE_COHERE_MODEL
#> 38 nvidia.key (not set) default NVIDIA_API_KEY
#> 39 nvidia.model (not chosen) default MORIE_NVIDIA_MODEL
#> help
#> 1 which route `ask` uses: auto (own endpoint, then each provider with a key, then Ollama), own, ollama or a provider
#> 2 your own OpenAI-compatible server, e.g. http://localhost:1234/v1 (LM Studio), http://localhost:8080/v1 (llama-server -m /path/model.gguf) or https://api.example.org/v1
#> 3 API key for your own server (sent as a Bearer token)
#> 4 model name on your own server
#> 5 your Ollama server, e.g. http://localhost:11434 or 192.168.1.20:11434; off to skip Ollama
#> 6 Ollama model to use (default: the first one pulled)
#> 7 API key for an Ollama server that wants one
#> 8 your OpenAI API key (sent only to https://api.openai.com/v1)
#> 9 OpenAI model to use (`rmbl models --route openai` lists them)
#> 10 your Anthropic API key (sent only to https://api.anthropic.com)
#> 11 Anthropic model to use (default claude-opus-5-5)
#> 12 your Google Gemini API key (sent only to https://generativelanguage.googleapis.com)
#> 13 Google Gemini model to use (`rmbl models --route gemini` lists them)
#> 14 your OpenRouter API key (sent only to https://openrouter.ai/api/v1)
#> 15 OpenRouter model to use (`rmbl models --route openrouter` lists them)
#> 16 your Groq API key (sent only to https://api.groq.com/openai/v1)
#> 17 Groq model to use (`rmbl models --route groq` lists them)
#> 18 your Together AI API key (sent only to https://api.together.xyz/v1)
#> 19 Together AI model to use (`rmbl models --route together` lists them)
#> 20 your Fireworks AI API key (sent only to https://api.fireworks.ai/inference/v1)
#> 21 Fireworks AI model to use (`rmbl models --route fireworks` lists them)
#> 22 your DeepSeek API key (sent only to https://api.deepseek.com/v1)
#> 23 DeepSeek model to use (`rmbl models --route deepseek` lists them)
#> 24 your Mistral API key (sent only to https://api.mistral.ai/v1)
#> 25 Mistral model to use (`rmbl models --route mistral` lists them)
#> 26 your xAI API key (sent only to https://api.x.ai/v1)
#> 27 xAI model to use (`rmbl models --route xai` lists them)
#> 28 your Cerebras API key (sent only to https://api.cerebras.ai/v1)
#> 29 Cerebras model to use (`rmbl models --route cerebras` lists them)
#> 30 your Perplexity API key (sent only to https://api.perplexity.ai)
#> 31 Perplexity model to use (default sonar-pro)
#> 32 your Hugging Face API key (sent only to https://router.huggingface.co/v1)
#> 33 Hugging Face model to use (`rmbl models --route huggingface` lists them)
#> 34 your OpenCode Zen API key (sent only to https://opencode.ai/zen/v1)
#> 35 OpenCode Zen model to use (`rmbl models --route opencode` lists them)
#> 36 your Cohere API key (sent only to https://api.cohere.ai/compatibility/v1)
#> 37 Cohere model to use (`rmbl models --route cohere` lists them)
#> 38 your NVIDIA NIM API key (sent only to https://integrate.api.nvidia.com/v1)
#> 39 NVIDIA NIM model to use (`rmbl models --route nvidia` lists them)
if (FALSE) { # \dontrun{
mdllmconf(route = "anthropic", anthropic.model = "claude-opus-5-5")
mdllmconf(route = NULL) # back to the automatic order
} # }