Skip to content

Model Providers

A provider is an organization-scoped account on an AI model vendor — OpenAI, Anthropic, AWS Bedrock, OpenRouter, and others. You configure a provider once with credentials and connection settings, and it powers the models your agents run on. Everruns abstracts every vendor behind one uniform driver interface, so the same agent, prompt, and capabilities run unchanged whether the model is served by OpenAI, Claude, Gemini, or any OpenAI-compatible endpoint.

ProviderDriverNotes
OpenAIopenai, openai_completionsResponses API (recommended) and Chat Completions. Also drives OpenAI-compatible endpoints via a base URL.
Azure OpenAIazure_openaiOpenAI models deployed in your Azure OpenAI resource. A dedicated provider type.
AnthropicanthropicClaude models via the Messages API, with extended thinking.
Google GeminigeminiGemini models, with implicit and explicit context caching.
AWS BedrockbedrockModels hosted on Amazon Bedrock via the ConverseStream API.
OpenRouteropenrouterOne key for a large multi-vendor catalog, with provider routing controls.
Microsoft MAImaiMicrosoft MAI models via Azure AI Foundry, with API-key or Entra ID (OAuth) auth.
Fireworks AIfireworksFast, low-cost inference for open models (Llama, Qwen, DeepSeek, Kimi, GLM, gpt-oss, …), with automatic model discovery.

Need a vendor that isn’t listed? Any OpenAI-compatible endpoint works through the OpenAI provider with a custom base URL (use the dedicated Azure OpenAI provider for Azure deployments), and embedders can register additional drivers through the platform definition.

Providers are managed by organization admins:

  1. Go to SettingsProviders.
  2. Click Add provider and choose the provider type.
  3. Enter the credentials (API key, or the provider-specific fields described on each provider’s page). Credentials are validated before they are saved.
  4. Save. Everruns discovers the provider’s available models and makes them selectable for agents and sessions.

You can configure more than one provider for the same vendor — for example two Azure OpenAI regions, or a direct OpenAI key alongside an OpenRouter key.

Providers and connections look similar but are deliberately separate:

ProviderConnection
ScopeOrganizationUser
PurposeInfrastructure that runs agentsA user’s identity on an external service, used by tools
Configured inSettings → ProvidersSettings → Connections
ExamplesOpenAI, Anthropic, BedrockDaytona, GitHub, Slack

Use a provider to decide which model runs your agents. Use a connection to give an agent access to an external tool or service.

Agents and sessions bind to a specific model on a specific provider. Because the driver interface is uniform, you can move an agent from one provider to another without rewriting prompts or capabilities. See Migrate between providers for the model-resolution rules and the API calls to add a provider, switch an agent’s default model, or run an A/B comparison per session.

  • Credentials are encrypted at rest with AES-256-GCM envelope encryption.
  • Credential values are never returned by the API — only a “configured” flag is exposed.
  • Resolution is fail-closed: each organization resolves its own configured credentials. A turn with no configured provider fails with a clear error rather than running on another organization’s credentials.