Skip to content

AI providers

Settings → AI Providers (/admin/settings/ai/providers) is where the LLM judge-vendor credentials live: the API keys — and the per-vendor concurrency bound — for the server-side eval judge. This page is credentials only; it doesn’t pick which vendor is active (that’s Evals:Agent:Provider on Evals), and it no longer holds embedding credentials — those moved to Embeddings.

Configure one or more vendors to enable the server-side LLM-as-judge runner. When several are configured, the active one is chosen on Evals; the judge model is set there too (Evals:Agent:Model), not per-vendor here.

KeyRangeDefaultDescription
Evals:ServerRunner:Anthropic:ApiKeysecretThe Anthropic API key. Stored encrypted at rest.
Evals:ServerRunner:Anthropic:MaxParallelJudges1–164Judge fan-out bound for this vendor.
KeyRangeDefaultDescription
Evals:ServerRunner:OpenAI:ApiKeysecretThe OpenAI API key. Stored encrypted at rest.
Evals:ServerRunner:OpenAI:MaxParallelJudges1–164Judge fan-out bound for this vendor.

Kurrent AI is Capacitor’s fully-managed judge and embedding service — Kurrent-hosted, with no API key to supply, available on the Team and Enterprise plans. Learn more about Kurrent AI and how it’s gated across plans.

Its API token, endpoint, and gateway are managed by Kurrent (set at deployment); the only editable setting here is the concurrency bound:

KeyRangeDefaultDescription
Evals:ServerRunner:KurrentAI:MaxParallelJudges1–164Judge fan-out bound for this vendor.

Hosted or on-prem:

  • Hosted Cohere API — set just the API key.
  • On-prem / airgapped deployment — set the base URL to your API base, e.g. https://cohere.internal (omit /v2/chat; it’s appended). The key is then optional.
KeyRangeDefaultDescription
Evals:ServerRunner:Cohere:BaseUrlstringBlank uses the hosted SaaS API. Set for an on-prem deployment.
Evals:ServerRunner:Cohere:ApiKeysecretRequired for the hosted API; optional on-prem.
Evals:ServerRunner:Cohere:MaxParallelJudges1–164Judge fan-out bound for this vendor.

Bring-your-own, OpenAI-compatible — point the runner at OpenRouter or any compatible gateway.

KeyRangeDefaultDescription
Evals:ServerRunner:OpenRouter:ApiKeysecretThe OpenRouter API key. Stored encrypted at rest.
Evals:ServerRunner:OpenRouter:BaseUrlstringhttps://openrouter.ai/api/v1Optional; override for a compatible gateway.
Evals:ServerRunner:OpenRouter:MaxParallelJudges1–164Judge fan-out bound for this vendor.

Embedding provider and credentials moved to their own page — see Embeddings.

Estimated cost rates sync automatically from models.dev — no configuration needed. The page shows the pricing source, the count of priced models, and the last sync time, with a warning if the last successful sync is more than 48 hours old.

  • Evals — selects the active judge vendor and model, and sets server-runner run limits.
  • Embeddings — the embedding provider and credentials that used to live here.
  • Assistants — reuses these same vendor credentials.