Vendor claims and pricing, captured 2026-10-23 08:46 (UTC+8) with curl (raw copies in runs/2026-10-23/tools/ollama/vendor/)

https://ollama.com/download/linux and README (github.com/ollama/ollama):
  Install: curl -fsSL https://ollama.com/install.sh | sh
  "Ollama runs open models in two ways: - Locally, on this computer. Speed depends on the hardware. Large models are slow on a computer without a strong GPU. - In Ollama's cloud."
  README: "Start building with open models. Access the latest releases locally or in the cloud with complete privacy."
https://docs.ollama.com/api/openai-compatibility
  "Connect OpenAI clients to Ollama. Ollama supports a subset of the OpenAI API."
  "These examples connect to your local Ollama server. The client requires an API key value, but Ollama ignores it."
https://docs.ollama.com/faq
  "Ollama runs locally. We don't see your prompts or data when you run locally."
  "Ollama can run in local only mode by disabling Ollama's cloud features." ... OLLAMA_NO_CLOUD=1
https://docs.ollama.com/capabilities/structured-outputs
  "Structured outputs let you enforce a JSON schema on model responses"
https://docs.ollama.com/import
  "To import a single-file GGUF model, create a Modelfile containing: FROM /path/to/file.gguf" ... "ollama create my-model"
https://ollama.com/pricing
  Free $0: "Run models locally", starter cloud usage credits. "Running models on your own hardware is always unlimited."
  Pro $20/mo ($200/yr), Max $100/mo, Team $500/mo, Enterprise custom: cloud usage credits. Cloud model prices per million tokens listed.