AI provider matrix

Enterprise

Kumiko resolves the AI provider per tenant. The application features use the provider contract; they do not need to know which vendor handles a request.

Provider choices

Provider	Best fit	Network and key behavior
Anthropic	Claude production workloads	Anthropic API with a tenant-scoped API key
OpenAI-compatible	OpenAI, Azure, OpenRouter, Ollama, vLLM, llama.cpp, or another compatible endpoint	Per-tenant endpoint and model; local endpoints can run without a hosted API key
Mock	Tests, demos, and deterministic integration coverage	Scripted responses; not a production model
OpenAI-compatible transcription	Voice input through a compatible transcription API	Per-tenant endpoint and model
OpenRouter transcription	OpenRouter-hosted transcription models	OpenRouter API key and model configuration

Choosing a deployment shape

• Use a hosted provider when you want the shortest path to production.
• Use OpenAI-compatible routing when you need to switch vendors or point at a local model without changing application features.
• Use a local endpoint when prompts and inputs must stay inside your network.
• Use the mock provider in every integration test that does not need a real vendor response.

Provider selection does not replace data classification. Decide which tenants may send which fields to which endpoint, then enforce that choice in tenant configuration, secrets, and application policy.

Build your own provider

The provider packages are adapters. An application can build its own adapter against the public ai-foundation extension point for another vendor, an internal gateway, or a rules engine. The custom adapter owns request mapping, timeouts, retries, error classification, secret handling, and tests.