AI providers
Settings → AI Providers (/admin/settings/ai/providers) is where the LLM vendor credentials live: API keys and models for the server-side eval judge, plus API keys for the embedding providers used by judge-fact deduplication. This page is credentials only — it doesn’t pick which vendor or provider is active; that happens on Evals.
Judge vendor credentials
Section titled “Judge vendor credentials”Configure one or both vendors to enable the server-side LLM-as-judge runner. When both are configured, users pick the vendor at run time.
Anthropic
Section titled “Anthropic”| Key | Description |
|---|---|
Evals:ServerRunner:Anthropic:ApiKey | The Anthropic API key. Stored encrypted at rest. |
Evals:ServerRunner:Anthropic:Model | The judge model, e.g. claude-sonnet-4-6 or claude-opus-4-7. |
OpenAI
Section titled “OpenAI”| Key | Description |
|---|---|
Evals:ServerRunner:OpenAI:ApiKey | The OpenAI API key. Stored encrypted at rest. |
Evals:ServerRunner:OpenAI:Model | The judge model, e.g. gpt-4o. |
Kurrent AI
Section titled “Kurrent AI”Available on the Team and Enterprise plans. On other plans, bring your own OpenAI or Anthropic key above.
The API token, endpoint, and gateway are managed by Kurrent (set at deployment) — only the model is overridable:
| Key | Description |
|---|---|
Evals:ServerRunner:KurrentAI:Model | The judge model. |
Cohere
Section titled “Cohere”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.
| Key | Description |
|---|---|
Evals:ServerRunner:Cohere:BaseUrl | Blank uses the hosted SaaS API. Set for an on-prem deployment. |
Evals:ServerRunner:Cohere:ApiKey | Required for the hosted API; optional on-prem. |
Evals:ServerRunner:Cohere:Model | The judge model. |
Embedding vendor credentials
Section titled “Embedding vendor credentials”API keys for the embedding providers used by the judge-fact semantic deduplication pipeline. Select which provider is active on the Evals page.
Voyage
Section titled “Voyage”| Key | Default | Description |
|---|---|---|
Embedding:Voyage:ApiKey | — | Voyage API key. Required when judge-fact dedup is enabled. |
Embedding:Voyage:Model | voyage-4-lite | Voyage embedding model. |
OpenAI
Section titled “OpenAI”| Key | Default | Description |
|---|---|---|
Embedding:OpenAI:ApiKey | — | OpenAI API key. Required when judge-fact dedup is enabled. |
Embedding:OpenAI:Model | text-embedding-3-small | OpenAI embedding model. |
Embedding:OpenAI:Dimensions | — | Dimension count, e.g. 1536. |
Model pricing
Section titled “Model pricing”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.
Related
Section titled “Related”- Evals — selects the active embedding provider and sets server-runner run limits.
- Assistants — reuses these same vendor credentials.