Skip to content

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.

ProviderCapabilitiesBest fitNetwork and key behavior
AnthropicTextClaude production workloadsAnthropic API with a tenant-scoped API key
OpenAI-compatibleText, transcription, read-aloudOpenAI, OpenRouter, Azure, Groq, Ollama, vLLM, llama.cpp, or another compatible endpointA connection of kind openai or openai-compatible with its own address (including /v1) and API key; local endpoints can run without a hosted API key
MockTextTests, demos, and deterministic integration coverageScripted responses; not a production model

A tenant keeps its providers as connections (AI providers screen, entity ai-connection). Each connection has a kind (anthropic, openai or openai-compatible), an address for compatible servers and its own write-only API key. OpenRouter is an openai-compatible connection; there is no separate OpenRouter package. The Standard models screen assigns a connection and a model to each job: text, images, transcription and read-aloud. A tenant can therefore run text on an Anthropic connection and voice on an OpenAI-compatible one.

The address must be a full http or https URL without a query string, a fragment or credentials. Tenant users can see the address, so an address like https://user:pass@host would leak a secret. Saving such an address fails with ai_foundation.connection_endpoint_invalid, both on a tenant connection and on the platform endpoint in the system config. A platform endpoint that still holds such an address, for example from a boot seed, is checked again on every read: the platform connection then counts as not configured and the server logs a warning. Put the key in the connection’s API key field.

  • 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.

For OpenRouter connections, ai-foundation can pin the data-handling policy.

  • providerRouting on a connection holds OpenRouter’s provider object (zdr, data_collection, allow_fallbacks, order, only). It is sent with chat requests, and only to openrouter.ai and its subdomains over https.
  • A connection marked requireEuZdr (“EU only, zero data retention”) must be openai-compatible and sit on an allowed EU origin, by default https://eu.openrouter.ai. It always sends zdr: true and data_collection: "deny", whatever providerRouting says.
  • createAiFoundationFeature({ enforceEuZdr: true }) applies the same policy to every connection of the installation, platform and BYOK connections included. euZdrEndpoints replaces the list of allowed origins.

The policy fails closed. A connection outside the allowed endpoints is refused on save and on every resolve. A request path that cannot carry the routing is refused with ai_foundation.connection_eu_zdr_request_not_routable. The query ai-foundation:query:connection-data-policy returns a connection’s effective routing for feature gates. The edit form does not expose providerRouting; set it through the connection write handlers.

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.