Providers

Providers are model backends AlphaBase can route through. Provider metadata is sourced from Models.dev and then merged with your connected credentials and local overrides.

BYOK Cost Model

AlphaBase is bring-your-own-key: you connect a provider’s credentials (API key or OAuth), and usage is billed by that provider directly to your account — AlphaBase does not add a markup or act as a billing intermediary.

One provider path requires no billing setup at all and is the default for new installs: Ollama cloud models (for example ollama/minimax-m2.5:cloud), which exist specifically so you can try AlphaBase end-to-end before connecting anything. Every other provider — Anthropic, OpenAI, Google, OpenRouter, GitHub Copilot, or any other Models.dev-listed or OpenAI-compatible provider — is billed by that provider once connected. See Models for how this affects task reliability and how to evaluate a connected model.

Runtime Provider APIs

Useful server routes:

• GET /provider
• GET /provider/auth
• GET /provider/capability-index
• POST /provider/:providerID/oauth/authorize
• POST /provider/:providerID/oauth/callback
• GET /provider/model-search?q=<query>

Connect A Provider

Typical flow:

1. open provider UI or /connect flow
2. authenticate via OAuth or API key
3. confirm provider appears in connected list
4. choose a model

Filter Provider Inventory

Use config-level filters:

{
  "enabled_providers": ["openai", "anthropic", "ollama"],
  "disabled_providers": ["openrouter"]
}

enabled_providers is an allowlist. If present, all non-listed providers are hidden.

Provider Override Schema

Each provider.<id> can override provider or model behavior.

{
  "provider": {
    "openai": {
      "options": {
        "apiKey": "{env:OPENAI_API_KEY}",
        "timeout": 300000,
        "setCacheKey": true
      },
      "models": {
        "gpt-5": {
          "options": {
            "reasoningEffort": "high"
          },
          "variants": {
            "fast": { "disabled": true }
          }
        }
      }
    }
  }
}

Supported common option fields:

• apiKey
• baseURL
• enterpriseUrl (notably for GitHub Enterprise Copilot auth)
• setCacheKey
• timeout (number or false)

Custom Provider Pattern

You can define non-default providers via provider records (for example OpenAI-compatible gateways), then route models through them.

Model Search (Model-First Onboarding)

/provider/model-search groups matching models by canonical family and ranks provider options by first-party/bundled/connected status. This powers “add model first, then choose provider” workflows.

Troubleshooting

If a provider is configured but unusable:

1. check runtime/capabilities
2. verify env key scope and endpoint URL
3. verify provider is not excluded by enabled_providers / disabled_providers
4. confirm timeout/baseURL overrides are valid
5. if the model intermittently fails, check whether it has been classified degraded from recent evidence — see Models; this self-heals as soon as the model’s recent attempts improve.

See Troubleshooting.